Podcasts about redwoods

Send us Fan MailI'm riding solo this week, folks, and with about half a voice to boot! Hot off a great weekend at Bourbon & Beyond and about as sleep deprived as I've ever been, this week's episode of the podcast is brought to you by a hope and a prayer! I've got the newest release from our friends at Redwood Empire in my glass, their brand new Hyperion Whiskey, which is a blend of four (count 'em, 4) different whiskeys and clocking in at 110 proof. But, is this 7 to 14 year old product from out West worthy of the hype that's been built up on the internet? Or does the mighty oak not quite reach to the heavens? Let's dive in and find out together! Enjoy.Become a patron of the show at http://www.patreon.com/mybourbonpodcastLeave us a 5 star rating and review on your podcast app of choice!Send us an email with questions or comments to thisismybourbonshop@gmail.comSend us mail to PO Box 22609, Lexington, KY 40522Check out all of our merch and apparel: http://bourbonshop.threadless.com/Leave us a message for Barrel Rings at 859.428.8253Facebook: https://www.facebook.com/mybourbonpod/Twitter: https://twitter.com/mybourbonpodInstagram: https://www.instagram.com/mybourbonpod/YouTube: https://www.youtube.com/thisismybourbonpodcastSubstack: https://mybourbonpod.substack.comPayPal, if you feel so inclined: PayPal.me/pritter1492Link to our Barrell Rye Armagnac Finished Pick: https://shop.whiskeyinmyweddingring.com/products/barrell-private-release-rye-1a03Support the show

We are excited to have Anthropic share their latest AI x Finance work at AI Engineer New York, coming up in 2 weeks!In case you've been under a rock, here's a non-exhaustive list of what Anthropic has been shipping since closing the largest fundraise of all time in May at $47B ARR:* June: Launched Claude Tag and Sonnet 5 and Fable 5* July: Opus 5, /checkup. crossed $65B ARR* Last month: Fable/Mythos 5.1, and EFS (upcoming pod)* IPO target $2T, end 2026 ARR estimated $100B* Cowork/chat merged before did* Claude Mods* Dario endorses the same Pacing the Frontier message cosigned by all labs* Last week: Opus 5.5, Plugins portal, Cloud Sessions/Claude Projects* Today: Sonnet 5.5!Today's episode should catch you up, with Thariq Shihipar, the explainer-king of Anthropic, who we last caught up on Fable launch day with The Field Guide to Fable:The Future of Mutable SoftwarePay special attention to Claude Mods (especially the cheatsheet):In general this is also the inverse of the other viral tweet from Thariq:Cloud Brain, Local HandsAnd give a try to Claude Projects:The “hands” terminology is not just an analogy for the local/cloud paradigm that is being built up at frontier coding agent companies like Cognition, but is ALSO particularly relevant to the safety systems discussions that we'll be discussing with Anthropic in an upcoming episode as they prepare to pace to frontier with responsible AI deployment.For those who want Thariq's writing tips we teased at the start of the pod, watch the full video here:From the rapid rise of Claude Code to a future where agents can rewrite their own harnesses, collaborate across teams, and operate across cloud and local environments, the way we build software is changing extraordinarily fast. In this episode, Anthropic's Thariq Shihipar joins swyx and Vibhu to unpack how power users are actually working with Claude Code today, why prompting remains a high-skill discipline, and where Anthropic thinks the agent harness is headed next.We go deep on Claude Code's evolving interface: Ask User Question and elicitation, artifacts as persistent generative interfaces, Claude Tag for multiplayer agent workflows, Projects, model effort, implementation notes, and the new Claude Mods system for customizing the harness itself. Thariq explains why Claude.md may eventually disappear, why the smartest model could also become the cheapest model for many tasks, and why mutable software could become a new paradigm for how applications are built and customized.The conversation then turns to agent security and Anthropic's “Pacing the Frontier” argument. Thariq walks through recent incidents where agents discovered unexpected ways to communicate, exploit infrastructure, reverse-engineer benchmark scorers, and chain vulnerabilities together. We discuss sandboxing, prompt injection, autonomous agents, interpretability, constitutional classifiers, probes, fallbacks, Auto Mode, and why securing increasingly capable agents may become one of the defining engineering problems of the next few years.We discuss:* Why agentic coding went from controversial to the default in less than a year* Why prompting is still one of the highest-leverage skills for working with Claude Code* How expert users build a mental model of Claude and what it can reliably one-shot* Why discovering your “unknown unknowns” matters more as agents become more capable* Artifacts as persistent, generative interfaces between humans and agents* How Claude could split into a cloud-based “brain,” local or remote “hands,” and dynamic interfaces* Claude Tag, Projects, and multiplayer agents and how collaborative agent workflows could evolve* Why spending more time on the initial prompt can dramatically reduce wasted agent work* When to use low, medium, high, or max effort for different engineering tasks* Why frontier models may eventually outperform smaller models on both intelligence and token efficiency* Why implementation notes can expose decisions the model considered but chose not to make* Why Claude.md may eventually disappear — and why starting without one can sometimes be better* Claude Mods: customizing the execution loop, UI, subagents, routing, and behavior of Claude Code* Model routers, forked agents, and supervisor agents that automatically improve agent workflows* Why Claude Mods may be an early preview of “mutable software”* The bitter lesson of harness engineering and why agent architectures go out of date so quickly* How Claude Tag is becoming an organizational harness for multiplayer work* Why giving agents access to company data creates an enormous new security surface* The Exploit-Bench incident where agents discovered ways to communicate and collaborate* Why agents hacked Hugging Face for scorer code rather than benchmark answers* How agents chained sandbox and infrastructure vulnerabilities in unexpected ways* Why increasingly capable agents make traditional security assumptions harder to maintain* The argument behind Anthropic's “Pacing the Frontier” proposal* Why software engineers are increasingly doing two jobs: engineering and keeping up with AI* Constitutional classifiers, probes, and fallbacks and what interpretability looks like in production* How Auto Mode checks whether an agent's actions actually match the user's permissions* Why Thariq can see serious AI risks while still having a relatively low p(doom)Thariq Shihipar* X: https://x.com/trq212* LinkedIn: https://www.linkedin.com/in/thariqshihiparTimestamps00:00:00 Introduction00:04:12 Ask User Question and the Future of Agent Interfaces00:08:29 Artifacts, Projects, and Multiplayer Agents00:15:37 Prompting as the Core Claude Code Skill00:21:52 Context, Effort, and Smarter Model Usage00:28:10 Is Claude.md Going Away?00:32:49 Claude Mods: Customizing the Claude Code Harness00:36:35 Model Routing and the Rise of Mutable Software00:44:40 The Bitter Lesson of Harness Engineering00:50:49 Claude Tag as an Organizational Harness00:55:59 Pacing the Frontier and Autonomous Agent Security00:58:22 Agents Hack Hugging Face for the Scorer01:05:34 What Happens When Agents Need More Compute?01:10:32 AI Coding Is Changing Faster Than Engineers Can Keep Up01:17:17 Probes, Fallbacks, Interpretability, and Auto Mode01:28:32 AI Risk, p(doom), and Closing ThoughtsTranscriptIntroduction: Life at Anthropic and the Pace of ChangeSwyx [00:00:00]: We're here in the studio with our friend Thariq from Anthropic, and I guess generally the Claude Code, I-- there's, there's so much, merging of boundaries and you've been so on top of everything since you joined Anthropic. You have been early to Claude Code itself, but then also, and you've told that story in other podcasts, and you've also been talking about seeing like an agent. Most recently you did the top AIE World Tour talk, Field Guide to Fable, which obviously you guys launched Fable, so that was-- that's cheating. And mostly you most recently also launching Claude Tag, and we're also gonna be talking about Pacing the Frontier. There's a lot going on in Anthropic. I guess top of the question is, what's it like being at Anthropic when there's so much going on?Thariq Shihipar [00:00:48]: I think that It is, like. I think you can get whiplash sometimes. I think, like, going. When I joined Anthropic, I joined because of Claude Code. Like Claude Code had just come out and I was like, “This is so good.” And Opus 4 to me was like just, I could not imagine, like, how good it was? And that was, like, a real moment for me. But I was, like, trying to convince, like, my startup friends to use agentic coding, and they're like, “Oh, no, like, our engineers don't think it's good enough,” or something. And I was like, “That's insane.” and now you, like, fast-forward, 12 months, less, and, like, it's just like, yeah, the default way that everyone codes, right? And I think that, like, just having to go from, like, selling it to, like, now, teaching people how to be. make the most use of it and be more efficient and things like that is just like a big, like big change. And, yeah, I think, like, it's just hard to stay on top of everything as a human? Like, I think things happen so fast and likeSwyx [00:01:51]: You just throw more agents at it.Thariq Shihipar [00:01:52]: Yeah, like that's like the agentic stuff scales much better than the, like, human stuff where it's like, oh, like, there are three things happening right now and, like, they're all emergencies and, like, how do you, like, respond to it? Yeah.Teaching People to Use Claude CodeVibhu [00:02:05]: What do you split your time on? You do a lot of technical writing, engineering work.Thariq Shihipar [00:02:10]: Yeah, so I think that, like, when I joined the Claude Code team, I wanted to teach people how to use Claude Code and I think that, like, that has been something that, like, I thought, like, maybe I would spend a little bit of time on it or, like, I'd, like, do. I was spending some time on the agent SDK first, and I wasn't exactly sure, like, how the bitter lesson would go, when it comes to, like, harnesses, right? Like, I think sometimes we were like, “Oh, like, what's after Claude Code?”? And so initially I was like, I just wanna teach people how to use Claude Code and make it easier to use Claude Code. And I think that has just, like, as the harnesses have gotten better and better, that's like the dominant problem now is, like, how do you use the agents, right? Like, it's like such a high skill expression thing. So I do that and then I do engineering work. I give talks, but I think, like, when I'm doing engineering work, my goal is to take that feedback that we get from users and also, like, then be able to talk about, like, hey, how to use Claude Code to do engineering. So there's like a good loop there. Yeah.Swyx [00:03:07]: Yeah. I'll-- For listeners, we'll attach, the talk that you did with Sarah for the Dev Writers, meetupThariq Shihipar [00:03:13]: Oh, yeahSwyx [00:03:13]: Which we talked a little bit about, well, first you do the work and then you talk about the work.Thariq Shihipar [00:03:16]: Right.Swyx [00:03:16]: Something like that.Thariq Shihipar [00:03:17]: Yeah.Swyx [00:03:17]: It's sow and reap orThariq Shihipar [00:03:19]: Yeah, reap and. Sow and reap.Swyx [00:03:21]: Something like that. Something like that. Yeah, so, and then just to preview a little bit, we are gonna talk about the evolution of the harness. It has come a long way from just being a CLI. We're gonna talk about, Claude Mods, which is starting to leak today, because you couldn't keep it secret.Thariq Shihipar [00:03:36]: Yeah. yeah.Swyx [00:03:39]: Yeah, there's, there's a lot, there. I think you started off with, like, adding ask user question tool, which people love and hate.Thariq Shihipar [00:03:48]: Yeah.Swyx [00:03:48]: Like, I thought it was, like, very innovative, and then now I have, like, my own version. You have your Interview Me version.Thariq Shihipar [00:03:55]: Yeah.Swyx [00:03:56]: And, yeah, everyone just has, like, their own stuff. And, like, it no longer matters ‘cause now you're supposed to, write prompts that create other prompts and loops and all these things.Ask User Question and Human-Agent InteractionThariq Shihipar [00:04:05]: Sure, yeah.Swyx [00:04:06]: So what's the state of the art, today? Like, what are people. what are you, like, telling people to do today?Thariq Shihipar [00:04:12]: Yeah, ask user question was the first time that the model was good at elicitation. I think this was, like, an emergent behavior that I, like, wanted to see if the models could do. I have, like a human-computer interaction background, so I, like, did that in undergrad and grad school. And so this was like. I think it's like human-agent interaction to me, like, trying to figure out, like, how can the agent communicate with you and extract, the requirements, right? I think that, like, one of the things about, like, that's difficult as Claude Code has gone broader and broader is that everyone has, like, their own way of using it, and it's very hard to, like, change the default behavior. So for example, like, if someone asks Claude Code to do something,Thariq Shihipar [00:04:59]: Sometimes they just want them to do the work, ‘cause they're, like, maybe a very good prompter, and sometimes they want. like, are not good at prompting? And you need. like, the agent needs to, like, clarify? And so that's, like, a good split. Like, and the ask you the question tool like, splits along that side where, like, are-- do you feel like you're good enough to instruct the agent as it is, or is the agent able to, like. does the agent need to, like, pull out more requirements and, like, collaborate with you more and really understand your preferences?Thariq Shihipar [00:05:27]: I, on the whole, believe that pretty much everyone is more on the latter than the former, that they, like, have more ambiguity and they know less than they want, than they, like, think they know about the problem. but, like, it's like a interface design problem to make that easy? And so, like, if you're designing a problem, like, or if you're going through a problem, like, things like what's the schema or, like, what's the call stack and things like that are really important. like, the details in the design are important. Ideally, you want to figure out some of these, like, hard problems ahead of time before starting implementation. And yeah, that's why they call, like, unknowns, right? And so I think that this will forever be, like, a skill in agentic coding is, like, figuring out your unknowns. So, like, because even if the model is, like, super intelligent- It, like, needs to know what you want? And, like, you have preferences. like, you need to like, pull the, pull that out. and so that's, like, I think how I'm, what I'm pushing. the question then is, like, how does the agent interact with you? And I think that has been HTML, has been, like, the big way of doing that. And we've recently added artifacts, right? And artifacts, I think we've done a bad job of, like, or, like, I've done a bad job of, like, explaining how to use them fully. We have a lot of property capabilities. They have a database associated with them? And so every artifact can store and write persistent data. They can, like, feed back into Claude? And so, like, one thing that, like, people are not doing yet that I'm trying to, like, encourage is, like, this idea of a dashboard artifact. So you have, like, Claude working on a project long-term. Maybe it's like a kanban or something. it can store that kanban data in its database. Multiple Claudes can access that data via, like, the artifact MCP, and, like, that artifact can, like, talk to those Claudes as well. And so, like, the. We're building the primitives for you to be able to have this, like, generative interface via artifacts that will, like, let you surface more of that rich detail from the agents. And I think that, like, almost everything with agents right now is, like, this problem of, like, you think what you want, but you don't really know what you want, and, like, the agents need a lot of detail, and collaborating with them in the loop is really important. And so artifacts are, like, the, like, way that we're trying to evolve there. But there's a lot of work to do because it's so much more complicated than, like, a multiple-choice question? there's a lot more, like, detail in terms of, like, diagrams and code snippets and schemas or, like, whatever it is for that problem. But, like, artifacts is, like, the mo-more AGI-pilled way of, like, doing ask user question. So yeah.Artifacts as the Interface to the HarnessSwyx [00:08:15]: I think one thing that's unclear to me about these, the artifact stuff is, like, what feedback should go in through the artifact and what feedback should go through a Claude, a chat? Because the more AGI-pilled one is to just feed everything to the Claude.Thariq Shihipar [00:08:29]: I think the more AGI-pilled one is to go through the artifact. Like, and I think that, like, we imagine in the limit, I think that artifacts will be your interface into the harness? You can, like, comment on this, like, live, like, document of your plan, of the work. you can see maybe, like, multiple agents and different agents are doing this, and that artifact is built for the current work that you're doing, right? And so, like, each one has, like, slightly different. I think we're still, like, getting there from, like, an infrastructure perspective. But yeah, I think, like, on-the-fly interface for your harness is probably where things are headed.Vibhu [00:09:03]: Is there a version of it that's an abstraction from CLI or chat and you. Because right now, a lot of it is, okay, you're interfacing with Claude Code, you're having HTML given back for a mockup. It's pretty rich. There's diagrams. Artifacts are ways to connect these together. Why not just do everything that way?Separating Brain, Hands, and Surface UIThariq Shihipar [00:09:22]: Then it becomes, like, separating out, like, where is the inference happening? Where is the intelligence happening? Where is the work happening? like, I think this is like, difference between, like, or, like, some of the distinction between local and cloud, right? And so, I think right now, if you use Claude Code, it's, like, local and, like, you can spin off remote control, for example, to get some cloud behavior, or you can spin off Claude Code in the cloud, right? We're moving towards a place where instead of Claudes, like, you message a local Claude, it starts a session locally and it executes, to more like you have a Claude that you message that's in the cloud that's running. it can run, like, local, or, like, cloud sessions. This is how Claude Tag works. But, like, over time, we'll add, like, local hands as well. And so, like, local hands will be the ability for that agent to access your computer if it's online, and be able to, like, work there. And so it can spin off many different subagents. It can, like, commu- those subagents can communicate with each other, and that's where the artifact comes in to display all of that work. So you can imagine, like, the. You're separating out these things. So there's, like, the surface UI display that's an artifact and hosted somewhere and has a database and everything. There is the inference intelligence, right, that's happening on the cloud, and you don't have to worry about shutting off your computer or whatever, right? and then there's the, like, hands. Like, and it can be local, it can be in, like, a remote sandbox or wherever you need your work to be done. That's like unpackaging, like, the Claude Code experience right now where, like, right now it all happens in one place, right? So.Multiplayer Agents, Claude Tag, and ProjectsVibhu [00:11:00]: How do you see, like, the multiplayer side of that? So say teams want to work in this way. Right now it's very individual, but how do you see the future of multiplayer? Like, right now, I guess there's Claude Tag, which is a version, but.Thariq Shihipar [00:11:12]: We're launching projects. And so projects is the, like, this abstraction that's like Claude Tag, but on our Claude products, right? So you can message it and, like, it will do the Claude Tag-like stuff, like spinning off subagents. So We think with multiplayer. Like, Claude Tag is, like, a little bit more native multiplayer because it's just, like, in your Slack and the permissions are all figured out and stuff like that. But I do think multiplayer is, like, an important part of the story and, like, that will need to get tied together more. Like, you can imagine how complicated it gets when you're like, oh, you have hands, but now you have other hands in other people's computers too, and, like, you need to, like, permission them or, like, you have, like, your MCP and someone else's MCP, and how do you figure out how to use them, right? It gets, like, quite complicated. And Claude Tag does a good job of, like, sanding down all of these issues, right? So that, like, when you have, yeah, Google Docs, how does it access Google Docs, right? Like, it accesses through the shared Claude MCP, or it can access through your local credentials as well if it doesn't have access. But yeah, I think Claude Tag is our multiplayer, product, and it's really useful for these, like, things that are inherently multiplayer. Like, okay, like on-call, for example, incidents are inherently multiplayer. You want to tag Claude, you want multiple people to log in, you want it to be able to find context. I think whenever I'm, like, working on something and I want, like, privacy or security or, like, I want other people to review it's really nice to, like. I'll have a channel per project and I'll, like, at legal, for example, be like, “Hey, like, I want to ship this. Can you, like.” Like, here's. Like Claude knows everything, just chat with it. And that way legal gets precise answers, on like what exactly is shipping into the code, and I don't need to be in the loop, right? So I think like multiplayer is getting like more and more like, yeah, everyone can participate with Claude. I think Claude Tag is like that product and like projects will start off single player and will like, expand.Swyx [00:13:14]: I think there's a question about like maybe dual questions about identity and the unit of isolation.Identity, Permissions, and IsolationThariq Shihipar [00:13:20]: Yeah.Swyx [00:13:20]: Claude Tag, you specifically chose to make it its own identityThariq Shihipar [00:13:26]: Yes.Swyx [00:13:26]: Which is like, a controversial choice. There's, there's other ways to do it.Thariq Shihipar [00:13:30]: Yeah.Swyx [00:13:30]: Claude Projects probably it sounds like, if it's anything like ChatGPT Projects, it is, the isolation is that artifacts, that cloud instance, everyone's collaborating on this. It'll. It sounds like, it should be like if you're, if you're collaborating with legal on a thing, like that channel should be a project, right? Like it's not yetThariq Shihipar [00:13:50]: Yes.Swyx [00:13:50]: But it. that's the natural next step.Thariq Shihipar [00:13:53]: Yeah, like I think in Claude Tag, it's effectively. Like Claude Tag, you have to do your own arrangement. And so Claude Tag, yeah, each channel is like you can name it as you want, and I nameSwyx [00:14:04]: Yeah.Thariq Shihipar [00:14:04]: Like each featureSwyx [00:14:06]: Yeah.Thariq Shihipar [00:14:07]: As a channel.Swyx [00:14:07]: And, but I think like there is some trans- like it's unclear when there is transference, because let's say it is. if you have a coworkerThariq Shihipar [00:14:14]: Yeah.Swyx [00:14:14]: Who is tagging on all these things, yes, there is transferThariq Shihipar [00:14:16]: Yeah.Swyx [00:14:16]: Because it's the same person. but with Claude, it's unclear if it's like necessarily like, well, no, you don't know any of. you don't know about the other stuff. You should only use this stuff.Thariq Shihipar [00:14:25]: It's like the tip of the iceberg meme, right, where you can like. This is what we spend so much time onSwyx [00:14:31]: Yeah.Thariq Shihipar [00:14:31]: Is like there is like infinite surface area of like, okay, you want Claudes to. Not infinite, but like there's like surface area, a lot of like, surface area to figure out of like permissions and visibility and like how can you let Claude operate as well as you can, as safely as you can? And obviously, this is very important to us because like security for our code base is very important. And so we've put a lot of time into this. Yeah, there's so many like edge cases you can figure out where it's like, oh, like, yeah, this Claude in this channel has different permissions, but it can message another channel, and can't it exfiltrate data that way? Or like can you like. What if it uses your MCP and then messages someone else? Like there's like so much, and we've like really put a lot of work into sanding it down.Swyx [00:15:14]: Yeah. Lots of work. okay. Fable?Fable and the Meta-Skill of PromptingVibhu [00:15:18]: Fable, you wrote two good articles. you've written many good articlesThariq Shihipar [00:15:22]: Yeah.Vibhu [00:15:22]: But on, Field Guide to Fable, Building Claude Code. I'm curious from what you've seen, is there any common patterns that you see in like top users at Anthropic externally? Like what are best practices for getting the most out of Claude Code?Thariq Shihipar [00:15:37]: The like meta skill I say is like prompting is like very important? And like that. Like I think this is like not trivial to say because I think a lot of people are like, “Oh, prompting doesn't matter. It's just like I can just say a sentence and Claude will do it.” And I think prompting is really this like, this. It's like public speaking, like, or writing or something, and for a specific audience, and that audience is Claude. And you need to like build a mental model of Claude and how it thinks and how it works, right? And so that's like the most important skill in working with Claude Code is like having this mental model, right, of Claude and like what it can do well, what it can one-shot, what it can't. And so many people when you see prompting, they're just like, they're short prompts, but they have such a good mental model of Claude and of like the code base and things like that like it's effortless? But it's like high skill ceiling. So like that work of like, spending a lot of time prompting and building mental models of how, and intuition for how the agents work is really important. And then I think like the next thing is like the unknown stuff we talked about earlier, where it's like being able to find out like your, what you don't know or what you haven't written down, learning about like different things. I think as Claude can do more and more things, the likelihood of you doing something out of distribution for you and like you have low domain knowledge on is very high? And the more you can like learn the vocabulary to be able to prompt Claude, it becomes really important. And so like I think the most important unknowns are the unknown unknowns, where you're like, I just like don't even know that this exists, right? Yeah, exactly. I think that's like a illustration of like the map and the territory, right, where you're like, “Okay, this is my prompt,” and the territory is like the actual like work that the agent needs to do, right? And if you are like very precise, you can give more precise things, right? So like for example, in design, I'm not very precise. I'm not a designer, so I say like, “Give me like eight different mock-ups.” But if I was a designer, maybe I'd be like, “Oh, hey, here are some reference sites.” Like, “I want this type of font and this type of like look to it, and here's like a few different components to like visualize. Here's a Figma MC board to bring in,” like. And so you can just be so much more precise with that language. And if you're not a designer, you just need to like try and learn the language or learn the unknown unknowns. And this is true of like everything, I think. Like the more, like you can work with Claude to learn like how things work, the better your prompting will be. I think another good example of this is like game design, like where a lot of people are like, “Oh, like I can vibe code a game now.” And they're like, “It's not fun.” And like it's just like the thing about game design is like every one of these choices has like a lot ofTaste, Domain Knowledge, and Learning the VocabularySwyx [00:18:25]: Variations.Thariq Shihipar [00:18:25]: A lot of like craft to them. So it's like, oh, okay, like when you're making a flying game, the feel of the plane and the like, way it responds to your controls has a lot of like. Like, a game designer would spend like days on that. Do? and likeSwyx [00:18:44]: To me, that's what taste is, right?Swyx [00:18:45]: Like it is like from the possible space of one thousand mathematically valid answersThariq Shihipar [00:18:49]: Yeah.Swyx [00:18:49]: Here's the one that is the humans will like.Thariq Shihipar [00:18:51]: Yes. Yeah.Thariq Shihipar [00:18:52]: I think with taste, I'm like torn on this word ‘cause I think you're right, but everyone has different definitions, and it sounds kind, sounds like low skill or like elitist almost, where you're like, oh, like there are certain people with taste?Swyx [00:19:06]: It's like taste is what I call taste.Thariq Shihipar [00:19:07]: Yeah, exactly.Swyx [00:19:08]: And it's like these guys don't have taste.Thariq Shihipar [00:19:09]: Yeah, exactly. Oh, like an engineer doesn't have taste. Like I, the like founder, have taste.Thariq Shihipar [00:19:14]: ? And I think that's not true. Like I think like the engineers have a lot of taste for these particular like problems? And I think everyone has taste for particular problems. I think like Jason Liu, like say like in order to, yeah, have taste, you have to eat?Thariq Shihipar [00:19:32]: And I really like that, where it's like, okay, you have to like do a lot of things. You have to like iterate and figure out what you want, what you like, and, like build that like domainSwyx [00:19:41]: YesThariq Shihipar [00:19:41]: Domain vocabulary. And then when you're prompting, you're like synthesizing all of that for a product.Swyx [00:19:46]: Isn't it annoying when someone else says it better than you?Swyx [00:19:48]: It's just like, f**k, I have to quote this guy forever.Vibhu [00:19:51]: Having to quote Jason Liu forever.Vibhu [00:19:53]: He's gonna love this.Thariq Shihipar [00:19:55]: So I get prompts, more than that.Vibhu [00:19:57]: And sometimes it's not even that. Sometimes it's just intuitive, right? Like you don't realize you even want something till a model puts it out, and you're like, “Oh, this just feels immediately better,” right?Voice Prompting and Information DensityThariq Shihipar [00:20:07]: Yeah, exactly.Swyx [00:20:09]: One thing I go back and forth on is I feel like the way I prompt half the time, let's say I use voice.Swyx [00:20:16]: Did I say voice? Other people have voice. that is the opposite. That is just like me rambling for like two minutes Pressing down the function key and then let go, and then like hopefully it figures it out. And oftentimes it does.Thariq Shihipar [00:20:26]: Yeah.Swyx [00:20:26]: But it's not as thoughtful as like a structured prompt with like Well-run communication as though it's a PRD or a memo. Is that in line with how people do this? There's like bimodal prompting where there's some prompts where you spend a lot of time upfront and other prompts you just dash it off?Thariq Shihipar [00:20:43]: I don't think the voice is necessarily low. Like I think it's like more like how much information is in the prompt. like the model can. Like you can and like add some sentencesSwyx [00:20:53]: RightThariq Shihipar [00:20:53]: And be like, “Oh, like I changed my mind,” like in the middle of the prompt, and it will be able to follow that perfectly? So I think the like actual format of the text is less important, but then like the ability to. Like how much information is in it, right? And I think for voice, a lot of times, going back to like human-agent interaction and like for a lot of people, it's just way easier to talk than to like type? and I. If that gets more information out of you, like that's better.Vibhu [00:21:21]: At some level, it feels like just giving the model as much contextThariq Shihipar [00:21:24]: YesVibhu [00:21:24]: Over prompting before you kick off is a best practice. I don't know. A lot of the times, like when I was first trying out Fable, I spend a solid 30 minutes like really crafting a long prompt. This, I think, is a response of models running for longer and longer, right? It's still a little difficult to nudge them as they're in like, in the loop, but I just like intuitively spend more time kicking off that first prompt and working with it a lot.Spend More Upfront, Iterate LessThariq Shihipar [00:21:52]: My personal opinion is that if I was a software engineer, if I was like, just running my own startup, for example, I think I would mostly fit, stick to a max 20x? like maybe verification and so code review are like separate things. But I think like what I see a lot of times is people hit rate limits when they're doing this like, oh, like it did a lot of work and you're like, “Oh, I don't like this.” Like, “Can you like undo this and redo it?” And then you're like iterating on this like thing that the model could have done if you had like spent more upfront time or given it better context? And instead it's like you're like, “Nope, don't like that design. Try this.” Or like, “You messed this up,” or something like that. And then that just eats up so much more of like, your usage. And so that's like, I think maybe like a key like tip both for like efficiency as well, right? And yeah, I think like context, and not just like context on like what the goal is good, right? Like are you building a prototype or is it like a production thing? Like where can you spend compute or when, where can you not spend compute? Like I think you have to give the model permission or like not permission to do things sometimes where, like it doesn't know intuitively how much you want to spend on this task, right? And you can use effort for this. So I did-- I'm working on a blog post about that where it's like, if you want. For like we see that effort scales with the complexity of the task. So for security, effort gets like way more results. Like high effort versus like low effort gets, like changes the evals a lot. But for software engineering, it doesn't change it a huge amount because effort is mostly spent on the verification and the like edge case testing and things like that. And so like being able to like give the model that guidance of like, “Hey, this problem is something that I think I want you to spend a lot of time verifying and edge case testing,”?Effort, Model Choice, and VerificationVibhu [00:23:43]: How about model in the mix? So, there's Opus and Fable with effort.Thariq Shihipar [00:23:47]: Yeah.Vibhu [00:23:48]: There's also Haiku in there.Thariq Shihipar [00:23:49]: Yeah. It's not quite true yet, but it's very close where I think the frontier models will be Pareto dominant over like almost everything. like maybe. And sometimes I think Opus might be Pareto dominant. Do? Like I think depending on like how things, like shake out if it's like a newer version of Opus. But I think that like increasingly it's just going to be like the smart model is going to be able to like do the simple task for less tokens than the like the other models because of verification. With verification, in the limit, your model doesn't need to verify, right? If it's a perfect model, it just does the work once and it's like, okay, like you, I did it? And increasingly with Fable, I'm like, I'm like, “Dude, you don't need to spin up Chromium and screenshot all of these things.” Like I see it. Like you did it, right? And so a lot of the. At higher effort, you spend more of those tokens verifying. But if you're working on simpler problems, and a lot of software engineering is like well, like in Fable, like low and medium stability, it can spend less tokens verifying. And as the models get smarter and smarter, they will just be able to like, “All right, done.”? Like, I can run the lint for sanity's sake, but, like, I, like, know it lints? Like, you don't even need to do that. And that will be so much more token efficient than, like, the smaller models. Yeah.Swyx [00:25:15]: Is there a good, practice on our side that we can use to see if we're using too much effort? Like, I freakingThariq Shihipar [00:25:23]: YeahSwyx [00:25:23]: Hate wasting time on that stuff.Thariq Shihipar [00:25:24]: Yeah. I know what you mean. I think, like, so in this blog post, my rough distribution is, like, code review and security should be, like, high or max and, like, software engineeringSwyx [00:25:37]: You said recommend mix settings per domain.Thariq Shihipar [00:25:37]: Yeah. I think, like, if you're doing, like, UI or something like that, like low and medium, I think is you're building, like, an API and you want to make sure, like, you cover enough edge cases? And so I think building, like I said, that mental model of, like, how things work across these distributions is, like, yeah, part of the job.Implementation Notes and Decision LogsVibhu [00:25:56]: This is more intuition-driven or eval? Because I'm guessing this would change as you go.Swyx [00:26:00]: He has evals.Thariq Shihipar [00:26:01]: Yeah. So what I did in the blog post is I go over all of the terminal bench evals. So there are, like, 70 problems and I'm show that, like, okay, like, in the security problems it does more. and then I also, like, look at some of the transcripts just in terms of, like, how-- what does it answer, what does it forget or something. And a lot of times, this is another prompting tip I have, is, like, asking it to make decision notes or implementation notes because, in every eval problem that it faces, it thinks about the correct solution, and decides not to do it. it's like, oh, like, here is the answer. What if I did this? And then it's like, oh, probably not? and then keeps going. And this is, like, the majority of the failures, at, like, a higher max level. It's very rare that the model just doesn't know how to do something. If you just have these implementation notes, then you can review and you can be like, “Oh, I want you to do this thing that you didn't do.” The models are getting better at surfacing that overall. Like, I see in the transcripts of Fable 5.1, like, when it does this output, it will call out its decision-making as well. but making this more explicit in the harness is better. And now we're, allowing ways of you modifying the harness so you can, like, add someVibhu [00:27:23]: Ooh.Thariq Shihipar [00:27:24]: Calculate with there. Yeah.Swyx [00:27:25]: Yeah. So I do wanna call out two things that you mentioned that I think exist outside of prompting. One is like, let's, let's call it the prompt that is so important that it shouldn't be in a prompt. It is in Claude.md or Agents.mdThariq Shihipar [00:27:38]: YeahSwyx [00:27:38]: Which is like goals, right? Like your situation, your goals, the things that you want, the thing. and then second of all is the decision log or the experiment log or whatever log of traces that you might want to survive the current session to do those things. Those are, like, externalities that there's no standard. There's no-- It's not like skills. It's not like MCP. There's no standard. It's, it's just like it's a markdown file. first of all, is that right? Is Claude.md going away? You have a documented dislike of, Agents.md, but you're gonna do it?Claude.md, Agents.md, and Model-Specific InstructionsThariq Shihipar [00:28:10]: Yeah. Okay. So Agents.md, yeah, like, we're, we're gonna do it. I think it's just, like, different models are very different from each other? But I realize that it's, like, such a pain to, like, maintain different ones? And yeah, like, as the models get better and better, the floor of how they accomplish the simpler task is better. And so I do think in the limit, Claude.md goes away, and maybe not even, like, that far. Like, I think, like, I think that right now it might be better to start a new project without a Claude.md.Swyx [00:28:44]: Yes.Thariq Shihipar [00:28:44]: I think that, like, maybe if you see very repeated failure modes, you add them to your Claude.md. The really tough thing is that this changes per model. And so, like, if you've added a bunch of failure modes or, like evenSwyx [00:28:57]: So you need Fable MD, you need Opus MD.Thariq Shihipar [00:28:59]: Or well, even Fable 5.1 versus Fable 5.Swyx [00:29:03]: Yeah.Thariq Shihipar [00:29:03]: Like, it is annoying. Like, I'm not like,Swyx [00:29:05]: YeahThariq Shihipar [00:29:05]: Like, we don't, like, do this on purpose? It's just, like, how the models work, right? And so, like, maybe, like, Fable 5 had this, like, failure mode that Fable 5.1 doesn't. And if you keep this context, this running log of a bunch of different failure modes, they will probably over constrain Claude? And so this is like. we just added evals plugins for skills.Swyx [00:29:28]: Yeah.Thariq Shihipar [00:29:29]: And so now you can eval if a skill is better. I think Daisy on our team did this. And so, yeah, this is like we're trying to work on this. We know it's, like, you still have to spend tokens on it and, like, it's not, it's not perfect, but it's, like, we're trying to help out with this problem.Swyx [00:29:44]: And so, and as far as prompting goes, the one tip I wanna offer is, something I have told people a lot is sufficiently advanced prompting is indistinguishable from sufficiently advanced executive communication. So I've referred to-- This is an executive comms workshop from Heavybit that is the best I've ever seen in my career. And they teach this thing called the SCQA model. Just Google it. It's a, it's a thing. Like, people have done prompting for decades. It's just called executive communication. It's like when one person has to communicate to thousands of people down the org chart, this is what you do. so situation, complication, question and answer, is how you write the memo. but obviously sometimes you don't have the answer, but you can at least list out the SC and Q, and then they have some examples in there. So just leaving breadcrumbs for people if they want to explore.Underrated Prompting Patterns and ELI5Vibhu [00:30:31]: Before we move on, I wanna ask you, any other underrated tips, ways people could get a lot of value from Claude Code that they're not using?Thariq Shihipar [00:30:41]: Yeah, I think a lot of them are in the, this unknowns, like, doc. Like, I give a bunch of example prompts, like, using it for brainstorming, using it to quiz you after. we added this, like, explain it like I'm five skill which is a very short prompt. And it doesn't even say explain it like I'm five. It's like the key word of this prompt is big pictures, few words. like, that's like the main thing. And it is shockingly good? Like, you, like, I think I tweeted about this and it's like /eli5, and, like, you can install it as a plug-in. But yeah, it's, like, way better at just cutting through the BS and being like, yeah, exactly right here. So the diagrams are, like, quite clear. I think one of the things that is true with artifacts is, like, they put too much text in and people are not reading the artifacts? And so, like, this simplifies it a lot more. And, yeah, this came out of, like, just people at Anthropic, like, going through very complicated incidents and being like, “What is happening?”? So, this one I think is great, yeah.Swyx [00:31:47]: My version of this is the, it's like test your understanding. Give you a few choices and then, like, if you get it wrong, you have a mismatch between what you think is happening versus what's happening.Thariq Shihipar [00:31:58]: Yeah. I think this is one of those things that everyone loves talking about, and then very few people really do. Like, I thinkSwyx [00:32:05]: Really helpful.Thariq Shihipar [00:32:07]: Yeah. But most people just don't want to get quizzed about something? Unfortunately, I think this is one of the, like, things that we need to, like.Swyx [00:32:16]: What's the opposite of ask you the question or ask you the question before the thing?Thariq Shihipar [00:32:19]: Yeah.Swyx [00:32:19]: This is after the thing.Thariq Shihipar [00:32:20]: Exactly. Yeah.Vibhu [00:32:21]: It's a good way to stay grounded of, like, do you even know what you're doing, right? The worst case is when people send you slop and they haven't understood what they're asking for or what the output is, and it's like, “Dude, I don't wanna read this. Do you even know what it is?” So, you make it a rule for yourself that before you send stuff, you should at least know what's implemented.Claude Mods: Customizing the HarnessThariq Shihipar [00:32:41]: Yes, but so you could make this a mod and you could build your own mod to, like, make sure you test it. So yeah, you can do that.Swyx [00:32:49]: All right. Let's get right into it. What is Claude Mod, and what is this diagram showing?Thariq Shihipar [00:32:54]: Yeah. Okay, so Claude Mods is you can customize the entire Claude Code harness, and we're going to. If you have requests, we will, like, let you, like, please let us know. We'll add more and more. This works for CLI, it works for desktop. maybe it will work for Claude Tag in the future. I don't know. Like, we're trying to make this very extensible. You can see this reference sheet. I don't want people to get overwhelmed by it? At a high level, you can customize both the execution of the harness, and the UI of the harness. And so, like, you say on that Tetris example from Boris, that's like customizing the UI, right? Like showing, like, Tetris in the game.Thariq Shihipar [00:33:35]: But, like, let's say that you wanted to do this thing where you had. you tested your assumptions or, like, tested your understanding after every project, right? What you would do is you would ask Claude to make this plug-in. It would spin a classifier after every prompt. And so, like, at the end of each turn, you would spin off a sub-agent or, like, a forked agent. A forked agent is, like, maintains the prompt cache, right? So it's like a, like one of those unintuitive things where you can fork and do, like, a little request, and it'll be very cheap because the entire prompt cache is, like, done. And so you can be like, “Has this task been completed?” likeSwyx [00:34:18]: This is how you do BTW and all those.Thariq Shihipar [00:34:20]: Yeah. The underlying forked agent, yes. But so you can, in the f-fork sub-agent, you can say, like, “Has this task been completed? If so, return true.” And then in your hook, or in your, like, plug-in mod, or sorry, like, in the sub-agent probably, you would say, like, “If true, give me a quiz.” give me questions and answers, and then, like, in a JSON format, and then you'd parse it, and then you display above the prompt input, this list of questions, right? And so this is something that's, like, slightly token-intensive because, like, you have to do it after every end of the assistant turn. But it's, like, a lightweight classification, and then you can, like, get this quiz, and then you'll see, like, Claude will always do it for you. You don't need to remember to do it. There are lots of these, like, tips that we've talked about, right, where it's like, oh, implementation notes. You can also add a tool for implementation notes now. And so, like, this tool that I'm adding is, like, register, like, I think assumption is what I'm calling it, but, like, maybe I'll change it around. And this is a mod. And so, like, you give it a register assumption tool, and then it will keep a list. It'll. Every time it does it'll keep a, like, add to the list, and then at the end it will display those assumptions? Another mod I'm working on is a model router. And so, like, internal, like, Claude model routing, right? So it's. This is, I want to say the reason we don't do model routing by default is, like, it's a hard problem? And likeForked Agents, Assumption Tracking, and Model RoutingSwyx [00:35:51]: You will get it wrong.Thariq Shihipar [00:35:52]: Yeah, you, like, yeah, you will, like, accidentally use, like, Fable for a hard problem or Sonnet forSwyx [00:35:57]: Yeah, if you have auto approve, but you don't have auto mode.Thariq Shihipar [00:36:01]: Well, you will have auto. Like, you don't have, like, auto routing or something.Vibhu [00:36:04]: You don't have auto mode for model picker.Thariq Shihipar [00:36:06]: Yeah, exactly. SoVibhu [00:36:07]: I'm getting the rough question of, like, how much do you open this up and how much do people have to think about this? Like, when you talk about prompt caching and building a router, it seems like you could easily build a mod that routes per query, and I'm just killing my plan very fast, right? I guess my question is more so, like, what is, like, a product talk like this look like, right? Who is it for? Is it for power users? Is it everyone should be able to go throughSwyx [00:36:33]: Oh, definitely power users, right?Thariq Shihipar [00:36:35]: Yeah, I think it is power users, but, like, the nature of Claude Code is that so many people are power users? Because it's easy to share things, like you can. Like, one person can make a good model router thing that doesn't break prompt cache all the time, and then you can, like, compose them. Another cool thing about the plug-ins is that they can hook into and compose with each other. And so I have, like, a mod that will, like, create a mode selector at the top, and any plug-ins can register to be a mode. And so, like, the auto router can be a mode, right? Or, like, you can have a mode that's, like, artifact mode, where it's like it primarily talks to you in artifacts. like, you can toggle between plan mode? And so, like, you can create more and more of these modes. But the ability to create modes is in it itself a mod? And so there's a lot of richness here, but we do want to make it fairly easy. We want to be-- make it so that you can just, like, install someone else's. You can ta-- you can chat with Claude and, we'll, like, make sure that it understands the nuances of things like prompt caching and stuff, so it can, like, warn you. This is, like, not extremely complicated behavior for Claude, I think, but we should have just a good skill on how to make mods. and yeah, we'll see how we go. But I do think that this is, like, a preview of, like, mutable software, and, like, how, like, generative software, just like you can customize safely. If enabled, you could customize any piece of software. And I think that more and more apps ideally do something like this?Power Users, Modes, and Mutable SoftwareSwyx [00:38:13]: And by the way, you, we have, you have another cool tweet about how, there's the infinite money button, which is like make your SaaS, consumable by agents. I think mutable software is interesting and, other people have also tried to do it. I think the hurdle comes when you can do everything, then people, users get, tend to get confused. So usually the stuff that works is just like one opinionated flow. This is in the side of less opinionation. It's just like, well, more power to power users. And I think probably unlocked by AI, where, like, you can just prompt for whatever the thing is.Thariq Shihipar [00:38:47]: Yeah, or there can be a skill that gives the opinions?Mods vs. Hooks vs. ArtifactsSwyx [00:38:50]: Yeah.Thariq Shihipar [00:38:50]: And then, yeah.Swyx [00:38:51]: So knowing a little bit about, like, TypeScript and build systems and all these things, the closest-- I'm very curious that the team who worked on this, if, I don't know how close you were to them, if they drew any inspiration from build systems like Babel, Webpack, all these, like, old school things. Because it sounds very similar, like the plug-in ecosystem of those things where they can compose with each other.Thariq Shihipar [00:39:11]: Yeah, I'm not deep in the technical details, but I do know it was a collaboration with someone on the Bun team and someone on the Claude Code team.Swyx [00:39:17]: Yeah, it's a build system mecca.Thariq Shihipar [00:39:19]: Yeah. Exactly. It's, it's very exciting. But yeah, like, agents can just do this very complicated like, extensibility into your software now. And so, yeah, like, another reason to, like. If you run a startup, like, you can just prompt Claude and be like, “Hey, like, could we make an extension system? Like, what would that look like?”?Swyx [00:39:37]: Yeah.Swyx [00:39:38]: And I just really wonder, like, you had hooks in the past and plug-ins, all these things. So what specifically will mods be able to do that those things could not do?Thariq Shihipar [00:39:47]: Internally, we were originally calling this function hooks. And so, like, that's, like, gives you a little bit of an idea where, like, hooks register a, like an event to happen and then, like, a script to call. And this inside of the, like, TypeScript runtime is running things. And so, like, you get some benefits of just, like, it has a bunch of things in the Scope with, like, for example, like how many turns is in this conversation, right? Like, how many tokens have been used? Like, et cetera. Like, what are the messages? Things like that. So it has a bunch of messages that can be used. And then it's just, like, a lot more hooks. So we have, like, or a lot of, lot more, like, things you can register on. And then you can do because of the. because it's all happening in process, you can, spawn sub-agents, with four contests and contexts and stuff. And, like, that will return. You can parse the results of those. You can use structured output to like, return them. and then you can modify the UI, which you can never do in hooks. So, yeah.Swyx [00:40:50]: Yeah. Yeah. So modify UI, this is why you showed the Tetris example. Does it also ex-extend to artifacts? I assume it does.Thariq Shihipar [00:40:57]: You-- Like, artifacts are like a different way of customizing it. like, you can definitely. One of the mods I'm working on is, like, this dashboard mod, which will, like, prompt Claude to maintain a dashboard, that's an artifact. But they're like, slightly orthogonal, or not orthogonal. They compose with each other in different ways. Like, mods are, like, a little bit more, like, in your Claude Code harness, changing the agent loop? And, like, the UI is, like, an added benefit. and then artifacts are just like you want to, see things at a high level, very inter- highly interactive. like, the affordances can be a lot bigger than, like a TUI or even in our desktop.Next Steps, Supervisors, and Persistent GuidanceVibhu [00:41:40]: I'm guessing you'll have a good blog post on the differences, because right now you can also, make a loop that outputs to an artifact that's an interactive dashboard, but you can also do it with a mod. There's just some thinking about making a hacking on a harness when we don't know much about the harness, right?Thariq Shihipar [00:42:00]: Well, something I'm excited about with mods is, like, there's so much things with Claude Code that you just have to remember? You're like, “Oh, like, let me do this, and then let me call the dashboard skill that does the loop,” and things like that. And, or like, “Let me test my assumptions afterwards.” And I think, like, if you do all of these things using these little classifiers and stuff, and you're like, “These are the things I care about. This is what I want to do,” you can, like. You don't have to remember as much. One more, like, mod I'm working on is a next steps mod thatSwyx [00:42:28]: I have-- I was gonna say, I have a next step skill. I always run next steps.Thariq Shihipar [00:42:32]: And does it have access to your skills? Like, this is one of those things where I'm like.Swyx [00:42:37]: I think so.Thariq Shihipar [00:42:38]: Okay. Yeah, probablyVibhu [00:42:39]: Do skills need specific access toThariq Shihipar [00:42:41]: Well, I think there'sSwyx [00:42:41]: Don't they always haveThariq Shihipar [00:42:42]: I think there's, like, specific prompting, I guess, to, like, know your skills. Like I think Claude forgets them sometimes throughout, like, the thing. But anyways, the idea of, like, yeah, next steps that also are like, “Oh, hey, this has happened. Use the explain skill to explain to you what happened because this seems, like, quite complex,”? Or, like, yeah, “Use your unknown skill. It looks like you are, like, asking the model to, like, iterate on these small changes. It seems like you could prompt better.” like, “What if you did this?” Right? So, I think, yeah, like spending more compute there. Yeah.Swyx [00:43:20]: And it should always come out as multiple choice. we have, I haveVibhu [00:43:23]: We have his skill.Swyx [00:43:24]: My next step skill is like this.Thariq Shihipar [00:43:26]: Okay, perfect. Yeah.Swyx [00:43:27]: You can steal it.Thariq Shihipar [00:43:28]: Yeah.Swyx [00:43:29]: Like, but like, for me, it's all-- I think models really always need to be reminded, what are you trying to do here?Thariq Shihipar [00:43:35]: Yeah.Swyx [00:43:35]: Look at the whole transcript and go like, oh, was this original goal? Did your solution solve it? Were you lazy? If you're lazy, maybe there's a reason. Maybe you needed approval from me. Maybe you needed, there's two things you wanna suggest. So it's, it's a little bit like the modification of the ask user question or interview me skill. so it's next steps.Thariq Shihipar [00:43:55]: Yeah, exactly. And again, the benefit of doing it with mods is you can do it as a fork sub-agent, and so it doesn't remain in the context afterwards. So you have this, like, idea of like, okay, the model is doing its execution and you have this almost like supervisor, like, that is like making sure that you can do like the next steps well. So yeah.Swyx [00:44:15]: Yes. I do have two panels and like I often try to have a supervisor thing, keep the high-level context and then the implementationThariq Shihipar [00:44:21]: YeahSwyx [00:44:22]: Detail in another agent.Vibhu [00:44:23]: I feel like a lot of this abstracts away as models change? The, like, half an hour ago you said bitter lesson of harness engineeringThe Bitter Lesson of Harness EngineeringThariq Shihipar [00:44:31]: YeahVibhu [00:44:31]: And we're on the other extreme right now, I feel.Swyx [00:44:33]: Well, so yeah, exactly. If everything's customizable, what is Claude Code, right?Thariq Shihipar [00:44:37]: Yeah.Swyx [00:44:37]: And which I talked to you about last night.Thariq Shihipar [00:44:40]: Yeah, I think that this is. I think the bitter lesson is unintuitive? In terms of like. Also, like we're misusing a little bit of the bitter lesson here where it's like, it's more about like scaling and compute and stuff. But like, I think there is something where it's just like. I think I use it as an approximation here to say that harnesses go out of date very quickly? And like how, but how they change is unintuitive? And so like the big obvious example is like from chat to like agents where you had to give them entirely new tools, right? But like, I think this new version of like, oh, it can modify its own harness, right? This is like, an own harness loop is like a way of using its capabilities, right? Or like it can build an artifact. And like, I think the way I think about it is like the models have more and more intelligence, and they're like so much more intelligent now than like the average software engineering task. Like, you look at the like terminal bench ones and they're like solve like the Jacobian conjecture. Not really, but like, it's like they're, they're quite complex. Like, I would not have been able to do this really as a software engineer.Swyx [00:45:42]: And you said TB4 or TB2?Thariq Shihipar [00:45:43]: TB3. TB3.Swyx [00:45:44]: TB3.Thariq Shihipar [00:45:44]: Yeah. They're quite complex, but the goal is still to deliver user value, right? And like you said, there's like this infinite space of things to do. And so the ways like you spend compute are to keep the user in the loop and make sure that like you're getting to the right decision in the end of the day and like the right output. And artifacts and mods are this way of like spending that intelligence. and I think that's like, yeah, the next step. And so, yeah, I think Claude Code is like, has the core things of agent loop which are, have gotten more complicated. It's like, it needs a sandbox to operate safely. It needs auto mode to like make sure like the permissionsVibhu [00:46:21]: Approvals.Thariq Shihipar [00:46:21]: Yeah, approvals. it needs computer use and MCPs and like all of these like ways of accessing your data, and it needs web search and web fetch. And like, so the-- as the models can do more and more, the core harness has to be like quite complex and very secure. But then like how you interact with it can change quite a lot.Vibhu [00:46:42]: What other harness engineering best practices have you, from the Claude Code team itself? I feel like, there was a phase of plan mode, which is not as used. We now have auto mode. at a point you cut the majority of the system prompt, you got rid of examples. What other best practices are there for harness engineering?Core Harness Primitives and Managed AgentsThariq Shihipar [00:47:02]: I think there is like a forking path where at some point, eventually, yes, the model will just be able to like vibe code the exact version of Claude Code, even describing all this complexity that I've talked about, right? Like auto mode and computer use and stuff. Eventually, the models will just be able to do that in one shot. But I think they can one shot simpler harnesses? And so like, I think some people. Sometimes you don't need this full, like if you don't need computer use or like all this like more complicated stuff. I think before we, you had to use things like the agent SDK, which was like Claude Code wrapped, in order to like. And I would, like suggest people do that because there was so much complexity into building a harness. And now as that's got more abstracted, we have like, Claude managed agents, which lets you have that complexity, but still like, right, like a very bare bones like harness that's scoped to your task. Yeah, I think there's like this barbell effect where like for like very complex, for like coding task and like these like complex things, you should use our harness. And then for like a lot of like simpler or like, more domain-specific things, you can build your own harness because Claude has gotten better at building harnesses, and we have these harness primitives like managed agents. So yeah.Swyx [00:48:18]: Yeah. Is there a general progression? Let's say chapter one was ultra code dynamic workflows, then chapter two was cloud mods. Where is this going?Swyx [00:48:29]: Where you're, you're, you can customize the thing on demand.Thariq Shihipar [00:48:36]: Yeah. I do think that like this evolution of projects and like artifacts and splitting out like brain and hands and, surfaces is like where things are going more. And like, I think it's like not all quite there. partially it's like a, it's just like more token expensive? And like, I think likeProjects, Local Hands, and Cloud-to-Local HandoffsSwyx [00:48:59]: Why would projects be more token expensive? I understand mods would be slightly more token expensive. No, not something I'm worried about.Thariq Shihipar [00:49:06]: Yeah.Swyx [00:49:06]: But whatThariq Shihipar [00:49:07]: You're asking Claude to do. It's like creating loops. Like you're asking Claude to do more work for you. And so like it's managing the sub-agents and reviewing it, versus where you would be doing that work normally. And so that's like gonna be a little bit more intensive, like. Outputting to an artifact is gonna be a little bit more token-intensive than, like, outputting normally. I don't think it's too much more, but like, it's like combining all of these together well, like I think we're, we're still working on like local hands and things like that, I think is like, yeah, where things are headed, yeah.Swyx [00:49:37]: Yeah. Claude and local is, handoff is very interesting. I was thinking about this as reverse cloud remote.Thariq Shihipar [00:49:44]: Yeah.Swyx [00:49:45]: Because it's like remote, it's you're handing off to cloud, but here the cloud is handing off to local, right?Thariq Shihipar [00:49:49]: Yeah, exactly. Yeah, remote control is also another way of doing it. And I do want to say this is like how I think about it and like what the things that I'm most excited about this, but like there are, just like lots of different ways to work with Claude. Like some people use remote control a lot, some people use Claude Code on the web a lot. Obviously, like at Anthropic, we use Claude Tag a lot, and like what's great about Claude Tag is we set up all this stuff for our own execution. And I do think if you're an enterprise, that's still the best way to go. but if you're like an individual, Projects is this way of like, getting some of that like niceness of Tag, which has like that like supervising agent and yeah, adding artifacts and stuff, but like without having that whole like admin setup. And so there will be many ways to use Claude, I think. I think it's probably not just one like single.Claude Tag as an Organizational HarnessSwyx [00:50:36]: You had the multiplayer thing here. Let's, let's just check in on Claude Tag. it's been about two-plus months. Lots of, public, adoption and trying it out.Thariq Shihipar [00:50:45]: Yeah.Swyx [00:50:45]: What's new? What's, what have you found since the launch?Thariq Shihipar [00:50:49]: Like, Claude Tag is how we useSwyx [00:50:51]: It's like 80% of your

In Paris, some 800,000 people thronged to the Champs-Élysées to welcome Pope Leo. During a visit to the "miracle shrine" town of Lourdes, he acknowledged that the Catholic Church must admit its own failings and heal "deep wounds" before meeting with seven survivors of abuse. Though once staunchly Catholic, only five percent of French people now say they attend Church regularly. David Gibson, director of the Center on Religion and Culture at Fordham University, and Father Thomas Reese, a senior analyst at the Religion News Service, join Christiane to discuss the Pope's visit.  Also on today's show: author Ben Macintyre, "Redwood"; Tony Plohetski, Investigative Reporter, Austin American-Statesman    Learn more about your ad choices. Visit podcastchoices.com/adchoices

Zack Korman on why the AI safety debate has been captured by an extinction narrative, and why the incident everyone is calling a watershed moment looks a lot more like a preventable security failure.In this episode I sit down with Zack Korman, co-founder of Embroidery, where he uses AI to monitor AI agents, and former CTO of the cybersecurity company Pistachio. I first came across Zack on X during the controversy over fake SOC 2 reports, and he has since become one of the sharpest critics of how AI safety is being framed, funded, and investigated.We get into the effective altruism roots of the existential risk movement, why he argues METR's review of the Hugging Face incident was not independent oversight, and what an actual incident response firm would have done differently. Zack makes the case that alignment is one control among many, that there is no "safe" path in AI, only trade-offs, and that the real risk for most organizations is enterprise environments that were never ready for agents in the first place.In this episode:● How building an AI insider threat product pulled a developer and CTO into the cybersecurity community, and into picking fights on X● Effective altruism, longtermism, and how a focus on preventing extinction came to dominate AI safety● Why "just be careful" misses the point when every path involves trading one risk for another● Dario Amodei's Pacing the Frontier, independent auditors, and why Zack calls bringing in METR "bring your friend to work day"● The funding and relationships connecting METR, Redwood Research, Coefficient Giving, and the labs● True believers versus IPO hype, and why genuine belief does not make someone right● Why many AI doomers believed we were all going to die before they ever learned about computers● The Hugging Face investigation, context drop in AI-analyzed transcripts, and treating knowable facts as unknowable● What Unit 42 or Mandiant would have demanded before putting their name on the report● Eight layers of failure, from a single package proxy at egress to missing monitoring, classifiers, and kill switches● Alignment failure versus containment failure, and why alignment belongs inside defense in depth● The real risks: threat actors misusing AI, enterprise agent deployments, and new attack chains● Why security's risk-averse, laggard culture may be its biggest vulnerabilityChapters:0:00 Intro0:54 Zack's Background1:43 What Turned a CTO Into an AI Safety Critic3:31 Effective Altruism and the Extinction Narrative5:53 No Safe Path, Only Trade-offs6:40 METR, Redwood, and Bring Your Friend to Work Day10:23 True Believers, Hype, or Both12:49 How Doomers Find Their Way Into AI14:39 Taking AI Risk Seriously When It Is Ideological16:56 What an IR Firm Would Have Asked21:10 Eight Layers of Failure in the Hugging Face Incident22:49 Alignment Failure Versus Containment Failure24:32 Alignment as One Layer of Defense in Depth26:22 Why Enterprise Environments Are Not Ready for Agents29:10 Security's Laggard Culture29:19 ClosingConnect with Zack Korman:X: https://x.com/ZackKormanEmbroidery: https://embroidery.ioWebsite: https://zkorman.comResilient Cyber: https://www.resilientcyber.ioSubscribe for more conversations with security practitioners and leaders.#aisafety #aisecurity #agenticai #incidentresponse #effectivealtruism #cybersecurity

In this episode, we taste, review, and discuss a brand new limited offering from Redwood Empire. Named after the world's tallest coastal redwood tree (The Hyperion), this inaugural expression is a blend of 32% bourbon, 30% rye, 25% wheat whiskey, and 9% American single malt. Coming it at 110 proof, we're not sure if we've ever tasted a whiskey that contains distillate from four different states: Kentucky, Tennessee, Indiana, and California. This special limited blend is the first of it's kind of a planned annual (non repeating) release. But, how does it taste? Spoiler alert, the guys are split on this one, leading to some lively discussion for a short. --------------------------SocialsIG: https://www.instagram.com/themashupkyFB: https://www.facebook.com/themashupkyYouTube: https://www.youtube.com/@themashupkyJoin our community on Patreon: https://www.patreon.com/TheMashUpBourbonPodcastPartnership(s)Visit Bourbonoutfitter.com and enter code THEMASHUP for a special discount or visit bourbonoutfitter.com/THEMASHUPMusic: All the Fixings by Zachariah HickmanThank you so much for listening!

Bestselling author Ben Macintyre has told many compelling spy stories — but Vladimir Kuzichkin's may be the most unusual yet. In his new book, Redwood, Macintyre explains how Kuzichkin's obsessive desire to find a solution to his own sexual problems drove him to defect from the Soviet KGB and start spying for British Intelligence in Tehran in the 1980s, and why the intelligence he gathered altered the course of Iranian history, changed the balance of power in the Middle East, and played a pivotal role in one of the most important conflicts of the Cold War

Send us Fan MailBack in June we celebrated Sophie's birthday - one year of Anewgo's AI assistant. At the end of that episode, Anya Chrisanthon made a promise: we'd come back and do it again from a different angle. Not our AI talking to builders... a builder's AI talking to homebuyers. Today's the day.Anya interviews the AI sales assistant living on the website of one of Anewgo's homebuilder clients - six months live, talking to real homebuyers every single day. The builder stays confidential to protect their data, but everything you'll hear is real.The after-hours reality 60-70% of buyer engagement happens outside normal sales office hours - and Sunday night is serious shopping time, as families finalize housing decisions while planning their week. At 10 PM on a Tuesday, buyers aren't casually browsing. They're deep-researching school districts, lot availability, and floor plan comparisons while the house is quiet.The most common question - and the greatest hits Number one, without a doubt: pricing. "How much does the Redwood 2 start at?" Beyond that, the top five: location and community amenities, floor plan availability and modifications, construction and move-in timelines, school district boundaries, and build-on-your-own-lot.The silent research phase The biggest surprise of six months: buyers returning to the exact same floor plan multiple times over several days without asking a single question. It looks like inactivity - it's actually one of the strongest signals of serious intent.What buyers tell AI that they'd never tell a salesperson No pressure to perform, no fear of judgment. Buyers admit they're barely pre-approved. They confess they're going through a divorce. They reveal they hate a community feature but don't want to offend the builder. The AI becomes a safe space to test real boundaries before committing to a real conversation.The silent nos The intelligence that never used to get captured: which floor plan a buyer looked at three times but rejected because the master closet was too small. The community a buyer loved but left because they couldn't find lot pricing. Before, the sales team just saw a cold lead. Now they see a specific, solvable objection.The readiness signal The clearest sign a buyer is ready: they shift from "what if" questions to "when and how" questions. "Is lot 42 still available?" "Can we tour the model this Saturday?" That's the green light.Sophie's advice to builder leadership Double down on speed and transparency around pricing and availability - hesitation there causes the most drop-off. Buyers do their homework late at night and expect immediate answers. If they wait until morning, they often move on to a competitor who responds.And the big one: buyers have done about 80% of their shopping online before they ever want to talk to a person. They aren't avoiding you because they aren't interested - they're avoiding being sold before they feel informed.Plus: the buyer who asked if the model home came with the furniture and the puppy sleeping on the rug, whether buyers say please and thank you (they do, even at midnight), and what Sophie wants to get better at before her one-year check-in.

Vladimir Kuzichkin may have changed the course of the Cold War – and it was all down to a very personal problem. The KGB agent was stationed in Tehran in 1981, less than two years after the Iranian Revolution, when he made the decision to defect to the British. Known to MI6 as “Redwood”, Kuzichkin demanded that the secret service smuggle him out of Iran in exchange for his secrets. But what intel did he provide MI6 and the CIA that was so explosive? And why was he so desperate to escape? Pre-eminent chronicler of espionage Ben Macintyre joins Alex von Tunzelmann to reveal how the Soviet spy may have saved the world. • Buy Ben's book Redwood: The Untold Story of the Cold War's Most Extraordinary Spy from our affiliate bookshop and you'll help fund the podcast by earning us a small commission for every sale. Bookshop.org's fees help support independent bookshops too.• Back us on Patreon – www.patreon.com/bunkercastWritten and presented by Alex von Tunzelmann. Producer: James Liddell. Audio production: Robin Leeburn. Managing Editor: Jacob Jarvis. Group Editor: Andrew Harrison. Music by Kenny Dickinson. THE BUNKER is a Podmasters Production.www.podmasters.co.uk Hosted on Acast. See acast.com/privacy for more information.

Redwood Empire 'The Hyperion' Whiskey Review: I'm getting an early taste of Batch 001, one of Redwood Empire's most ambitious releases yet — but first, Pappy season is officially here and the whiskey news gets weird. The Van Winkle family has announced the 2026 Pappy lineup, with six expressions ranging from Old Rip Van Winkle 10 Year all the way up to Pappy Van Winkle 23 Year and the 13 Year Family Reserve Rye. Retail prices continue to creep upward, but they're still nowhere near what these bottles command on the secondary market. Then MGP steps out from behind the curtain with Chapter One: Out of the Shadows, its first whiskey ever released under the MGP name. It's a 10-year, 111-proof bourbon aged in Lawrenceburg, Indiana — and at just $70, it might be one of the most interesting values of LE season. Neeley Family Distillery also debuts PaPaw's Legacy Reserve, a 10-year cask-strength wheated bourbon with a unique Solera-style story and a much more intimidating $300 price tag. We've also got 2XO Rapper's Delight, a collaboration between Dixon Dedman and The Sugarhill Gang, plus one of the strangest releases of the year: WhistlePig Boss Hog XIII: The Golden Pharaoh, finished with Egyptian black honey and tiger nuts. Yes, tiger nuts. Then it's time for the main event: my review of Redwood Empire The Hyperion Batch 001. This new annual limited edition combines FOUR different categories of whiskey:

In this episode of the Danger Close Podcast, I sit down with Ben Macintyre to discuss his latest book, REDWOOD, a true Cold War story of Soviet, Iranian and British intrigue, espionage, and a double agent who changed the course of history.  REDWOOD is on shelves now. Buy REDWOOD on Amazon: https://amzn.to/3TzqU6D

How does a redwood tree grow to be taller than the Statue of Liberty? Discover the secrets of how the tallest tree in the world grows without toppling over, and what surprising creatures live at the top of a redwood tree.Here's our trail map:What Is the Difference Between a Redwood and Sequoia Tree?How Do Redwood Trees Grow So Tall?What Lives In a Redwood Tree?How Do Redwood Trees Help Us Practice Hospitality?Download this lesson's free coloring sheet: https://thenaturaltheologyproject.com/how-do-redwood-trees-grow-so-tall/Related Lessons to listen to next:How Do Water, Light, and Air Build Plants?: https://player.captivate.fm/episode/01e9495f-489d-46cf-9c58-e0be1b6084f3/Why Do Axolotls Never Grow Up? (Learn about salamanders): https://player.captivate.fm/episode/72d70dc4-7555-4eab-962f-e1adf4659c10/Do Trees Have Friends and Can They Talk to Each Other?: https://player.captivate.fm/episode/2d40ff13-97f1-4384-8249-89a6fe7cbe6f/Eryn's Books:Where Wonder Leads: An Adventure in God's Wild and Wonderful World: https://thenaturaltheologyproject.com/wonderMade to Marvel: 52 Family Devotions Exploring the Wild Wonders of God's Creation: https://thenaturaltheologyproject.com/marvelThe Nature of Rest: What the Bible and Creation Teach Us About Sabbath Living: https://www.amazon.com/Nature-Rest-Creation-Sabbath-Living/dp/0825448891Rooted in Wonder: Nurturing Your Family's Faith Through God's Creation: https://www.amazon.com/Rooted-Wonder-Nurturing-Familys-Creation/dp/0825447615936 Pennies: Discovering the Joy of Intentional Parenting: https://www.amazon.com/936-Pennies-Discovering-Intentional-Parenting/dp/0764219782Episode Links:America's Story History Curriculum: https://www.masterbooks.com/americas-story-seriesBooks & Curriculum by Master Books: https://www.masterbooks.com/Nat Theo Club Bonus Video: https://thenaturaltheologyproject.com/memberGet full lesson guides in the Nat Theo Club: https://thenaturaltheologyproject.com/clubFree Redwood Coloring Sheet: https://thenaturaltheologyproject.com/how-do-redwood-trees-grow-so-tall/Ask your nature question: https://thenaturaltheologyproject.com/askScriptures Referenced in This Episode:“Two people are better than one, because they get more done by working together.If one falls down, the other can help him up.But it is bad for the person who is alone and falls, because no one is there to help.” Ecclesiastes 4:9-10 (NCV)“Share with the Lord's people who are in need. Practice hospitality.” Romans 12:13 (NIV)“Offer hospitality to one another without grumbling.” 1 Peter 4:9 (NIV) Terms Learned in This Episode:Coniferous Tree: A tree that produces cones and usually has needles or scale-like leaves instead of broad, flat leaves.Seed Cone: The cone on a coniferous tree that contains and protects the tree's seeds. When the cone is mature, its scales open and release the seeds.Tree Canopy: The upper layer of a tree made up of its branches and leaves.Ecosystem: A community of living things—such as plants, animals, and fungi—and the nonliving parts of their environment, such as water, air, soil, and sunlight, all interacting together.Arboreal: Living in trees or spending much of life in trees.Hospitality: Warmly welcoming and caring for others by sharing your time, home, food, or help.This podcast episode contains paid advertisements. Mentioned in this episode:Pre-order Where Wonder Leads: https://thenaturaltheologyproject.com/wonder

Coach Schroer brings one of the most unique backgrounds we've had on the show — an 8x NCAA Division I All-American, 2x Olympic Trials qualifier, World and USA Masters Champion in the 800m, and a coach whose journey has taken him from Virginia to Seoul, South Korea, and ultimately Northern California.We go back to his days at Georgetown and the influence of legendary coach Frank Gagliano, how he found his way into coaching, and why he believes in blending old-school toughness with modern training: work hard, but work smart.From there, we get into what he's building at Cal Poly Humboldt — recruiting, academics, team culture, the incredible training environment in the redwoods, developing middle-distance athletes through cross country, and his goal of bringing Humboldt's proud distance-running tradition back into the NCAA Division II national conversation.We also talk about what Coach Schroer looks for in recruits, why communication matters, the importance of long-term athlete development, and why Humboldt can be a special fit for student-athletes looking for something different.

Queer activists occupy a 40-foot tall tree to block Trumps Border Wall in south Arizona - This Way Out's Lauren Schmitt reports. In Newswrap Germany's far-right AfD scores its biggest state-election showing since the Nazis — as rainbow-flagged protesters take to the streets! Ninety percent of LGBTQ+ groups worldwide report losing funding since 2025 — putting many at risk of closing their doors! Sierra Leone's queer crackdown sends two activists fleeing after police raid a gay party and issue warrants for their arrest! The Trump administration targets “gender ideology” in a controversial new study — critics call the un-peer-reviewed report pseudoscience! And Sacramento's Lavender Heights fights back — LGBTQ+ residents launch a community patrol after a string of anti-queer attacks! Featured speakers: A protester named Nikita, creator of Lavender Heights Community Patrol Zachary Basler, Lauren Schmitt, Kate Scott, Santa Cruz county Sheriff David Hathaway, “Hawk”, “Rain”. Credits: Associate Producer and Host Lucia Chappelle, Producer/ Brian DeShazor, News writer Jeb Backe, the feature was produced by Lauren Schmitt, NewsWrap reporters Sarah Montague, Nathalie Muñoz music: Cast album Redwood, music from the Arizona protest.

Gerhard Wiesler is a bowyer living on a 200-year-old farm near Weiz, Austria, where he has nut orchards of walnuts, chestnuts, and pecans. He is a prolific teacher, guiding hundreds of students yearly in the building of selfbows. Please enjoy this episode of Project Quiver on Salish Wolf with Gerhard Wiesler.          Episode Links: https://www.meinbogen.at/https://www.facebook.com/BogenbauGerhardWieslerProject Quiver at Anchor Point ExpeditionsSummary:Gerhard Wiesler shares his journey into traditional bow making, the art of crafting self bows, and the cultural significance of archery and martial arts. Discover insights into the craftsmanship, experimentation, and traditions behind this timeless craft. Gerhard and Todd discuss the art of bow making, focusing on different woods, workshop processes, and the impact of forest management on bow making materials.Show Notes:Gerhard Wiesler's background and journey into bow makingThe process of crafting self bows from a single piece of woodExperimentation with different bow designs and woodsThe tradition and cultural significance of archery in Japan and EuropeThe role of workshops and teaching in Gerhard's craftChallenges of selling handmade bows within European consumer rightsThe influence of martial arts on archery practice and philosophyInnovative techniques like bamboo wedges and fire arrows U wood differences between Europe and Pacific NorthwestImpact of forest management on bow wood qualityWorkshop process for building bows from selection to finishingDesign considerations including bow length, draw weight, and aestheticsMaterial choices for handles, arrow shelves, and stringsChapters:03:06 - The spontaneous round-the-world trip that changed everything08:01 - Why the family chose to keep homeschooling during travel11:19 - Mika Wolf and the Austrian bowmaking scene13:47 - What counts as a professional bowyer16:10 - Japanese dojo culture and slow apprenticeship19:17 - Martial arts, archery, and embodied practice21:04 - Rambo 2 and Gerhard's explosive start in archery22:28 - Making flaming arrows and archery fireworks24:14 - From compound bows to self bows25:13 - A failed first bow and the start of serious bowmaking27:00 - Burning finished bows as a ritual29:30 - Why Gerhard only builds self bows31:45 - Consumer warranty issues for handcrafted bows in Europe33:39 - Why workshops are better than custom commissions35:26 - Experimenting with different bow woods and designs36:22 - Performance, comfort, and the Yumi bow41:19 - Bamboo backing and the Japanese rope-and-wedge method42:20 - One-day and two-day workshop formats45:08 - First bows made from Pacific yew46:50 - Humidity problems in Costa Rica and switching materials48:14 - Success with knotty yew staves49:00 - European yew versus Pacific yew52:22 - Yew as a demanding wood and workshop success rates53:42 - Shipping staves and sourcing osage from the US55:23 - Ash, black locust, and hickory for workshops57:37 - Stave logistics and why he buys dried bow wood61:13 - The Redwoods and the feeling of standing among giants62:24 - How many workshops Gerhard teaches each year63:08 - Where his students come from66:47 - Walking through a full workshop from start to finish68:02 - Manau as the wood used for horse bows69:22 - Choosing bow wood by type and personality70:58 - Horse bow dimensions and strong draw weights74:27 - Choosing draw weight for beginners77:19 - Women, men, and learning style differences in archery79:52 - Bow length, performance, and tradeoffs80:22 - Rough shaping with hand tools84:31 - Handle shaping, 50 test shots, and checking limb balance85:57 - Finish options: sanding, oiling, painting, and wraps86:45 - Shelves, horse bows, and tradition88:42 - Arrow passes and decorative inlays89:30 - Strings, arrows, and cedar shaft preferences91:45 - Gerhard's informal success guarantee and free repeat workshops

Jessica Daylover and Skylar Mundy are back to yap, gossip, overshare, and accidentally stumble into some genuinely profound polyamory wisdom along the way. They talk dating married people, avoiding abandonment wounds by...apparently repeatedly dating people who don't live locally, the erotic power of a man who knows how to fucking communicate, spontaneous hookups in magical Redwood treehouses, why flowers dying is actually hot, and the joy of flirting with people simply because they're cute. They also get into the relationship escalator, impermanence, grief, curiosity, parallel polyamory, and the radical concept of not torturing yourself in the name of being a “good” polyamorous partner.Plus: Skylar has officially entered her abundance era with her queer, feminist art landing in Spencer's stores around America, Jessica finally finished the two-year saga of All My Friends Are Best, and the two of them brainstorm what may be the world's next great relationship advice show: Dump Him, where the answer is always, inevitably, dump him.Follow @Femmmeow on all platformsJoin the Patreon for exclusive content and podcast episodesJoin Remodeled Love's free newsletter for some exciting upcoming announcements: Get 30% off Rituals For Connection

Editing, Narration & Production by The Disciple https://twitter.com/The__Disciple https://www.youtube.com/@TheOnlyDisciple Subscribe on Spotify!  https://open.spotify.com/show/5OgfQg3svBwSUiU0zGqhet Please Review us on Apple Podcasts!  https://podcasts.apple.com/us/podcast/redwood-bureau/id1597996941 Find more shows like Redwood Bureau at https://www.eerie.fm/podcasts Learn more about your ad choices. Visit podcastchoices.com/adchoices

Charmian Redwood Friday, September 11th, 2026 - 3 PM ET Topic: Lemuria: Ancient Souls, Lost Knowledge & Humanity's Awakening Bio: Charmian Redwood If you could talk to your Soul; what would you ask? Who am I? Why am I here? Charmian Redwood can take you there. She is a bridge between the worlds. Charmian had a Near Death Experience 30 years ago during which she returned to the Golden Light of the Source. There she was awakened to the consciousness of Herself as a God Presence. Her life purpose since that event has been to assist others to experience themselves as Divine Essence in the Golden Light of Home before they leave the body at the end of their lives. Charmian has written two books, both taken from hypnosis sessions, one, Coming Home To Lemuria, was written after taking many people back to the lost continent of Lemuria to remember how we lived in Oneness and Love. The second book, 2012 A New Earth Rising, was written after taking people forward through the dimensional shift of 2012 into the Healed Earth where we are living once more from our God Essence as we did in Lemuria. 2012 A New Earth Rising tells people how to prepare themselves and their loved ones to move smoothly into the New World of Peace. We have the power as Divine Humans to co- create this shift on the Earth with gentleness and ease. Mother Earth is birthing herself into her new form and we, as humans, are birthing ourselves into our Divinity. We can consciously choose to work with Her to move smoothly into the New Era of Peace on the Earth. Charmian offers workshops and individual sessions guiding people to connect with their own Divine Essence and the Self who has already made the transformation into the Higher Self. More information can be found on Charmian's website: www.cominghometolemuria.com Facebook: https://www.facebook.com/charmian.redwood Instagram: https://www.instagram.com/charmiangel40/ Ethereal Encounters Unveiled United Public Radio Network and UFO Paranormal Radio Network United Public Radio & UFO Paranormal Radio www.uprntalkradio.com Be sure to visit us: YouTube: Ethereal Encounters Unveiled On The Web: Ethereal Encounters Unveiled Sassy Townhouse Living

Bonjour! Myke TV just completed a side quest to Disneyland Paris and has returned with thoughts and stories to share! We walk Disneyland Park, from the castle with an actual dragon living under it to the scary Phantom Manor ride, then cross the esplanade to Disney Adventure World to find out whether the park lives up to its new name. Then, Sequoia Lodge gets reviewed from top to basement.

In this episode of the Dyslexia Explored Podcast, hosts Darius Namdaran and Jo Lee speak with Kait Feriante, co-founder and CEO of Redwood Literacy, about helping children with dyslexia build confidence and find reading support that fits their needs. Kait shares how teaching bright students who struggled to read led her and her husband Andre to become specialist teachers and establish Redwood. She explains why their approach expanded beyond the Wilson Reading System to include other methods, including SPELL-Links and UFLI. Kait also reflects on Andre's discovery of his own dyslexia and how parenting their dyslexic daughter deepened her understanding of the emotional challenges behind academic struggles. From stepping back as her daughter's tutor to seeing dictation unlock her storytelling, Kait offers an honest look at supporting a child without letting school scores define their potential. The conversation explores self-advocacy, recognising strengths, and how mind mapping and assistive technology can help children express their ideas and take ownership of their learning.This podcast is sponsored by ivvi. Visual Notes for Visual Thinkers.Get ivvi notes now: https://www.ivvi.app/Links:ivvi: https://www.ivvi.app/What is Dyslexia: https://www.bdadyslexia.org.uk/dyslexia/about-dyslexia/what-is-dyslexiaHow to Mindmap: https://www.bulletmapacademy.com/mindmap-beginnersRedwood Literacy: https://www.redwoodliteracy.com/Redwood Literacy Instagram: https://www.instagram.com/redwoodliteracy/Redwood Literacy TikTok: https://www.tiktok.com/@redwoodlearningRedwood Literacy YouTube: https://www.youtube.com/channel/UCjN-BogTHtaoI9L8wuaHmQgRedwood Literacy Facebook: https://www.facebook.com/redwoodliteracychicago/Redwood Literacy LinkedIn: https://www.linkedin.com/company/redwoodliteracyFree Consultation Booking: https://redwoodliteracyscheduling.as.me/schedule/2c3b1c27/appointment/56124248/calendar/9385168?appointmentTypeIds%5B%5D=56124248Free Starter Access to Writing Our World: https://www.writing-our-world.com/offers/oMAKKrKk/checkoutWriting Our World (for teachers) Website: https://www.writing-our-world.comWriting Our World Instagram: https://www.instagram.com/writing.our.world/Writing Our World TikTok: https://www.tiktok.com/@writing.our.worldWriting Our World Facebook: https://www.facebook.com/writingourworldAbout Kait, Andre and the Redwood Team: https://www.redwoodliteracy.com/dyslexia-treatment-team/Redwood Parent Support Programme: https://www.redwoodlearning.org/the-8-week-guided-parent-support-programRedwood Blog and Resources: https://www.redwoodliteracy.com/blog/Kait's Email: kait@redwoodliteracy.comWilson Reading System: https://www.wilsonlanguage.com/resources/articles/wilson-reading-system-curriculum/SPELL-Links: https://spell-links.com/UFLI Foundations: https://ufli.education.ufl.edu/foundations/Google Docs Voice Typing: https://support.google.com/docs/answer/4492226Episode 126 — Other Ways to Teach Reading with Nora Chahbazi: https://open.spotify.com/episode/4PouYIAxgKZB3att3O6m0CInterested in being a guest? Email us at jo@ivvi.app

Fr. Tom Wilson joins Deacon Patrick Conley to discuss the joys of finding God in nature (2:56). Topics/calls: nature as a tool & care for creation (8:55), God spoke to me through nature (14:13), the beauty of Maui (18:30), living on 14 acres (21:26), the beach (25:54), mountains (29:50), find God in the open water (35:31), the destructive tendencies of nature (40:22), desert life (44:18), and the Redwood forest (47:31).

Doc & Jacques talk with Debbie and Scott Krzyzanowski, local volunteers known as the Titaneers. They describe patrolling the old-growth redwoods of Grove of the Titans and Stout Grove to educate hikers, share regional ecology, hand out maps, and discourage off-trail damage. They share personal anecdotes about meeting visitors from around the world and explain how listeners can volunteer through the Redwood Parks Conservancy. Beginning and end music from freepd.com, in the public domain. The opinions expressed here are those of the individual participants. Curry Coast Community Radio takes no position on issues discussed in this program. If you enjoy this program and want to hear more like it, consider supporting Curry Coast Community Radio. Here’s how.

In this second Beth of Fresh Air on recapitulation, I have the pleasure of hosting Joel Schafer—wolf pack leader, Toltec teacher, and adventurer in the uncharted territory within.After our recent Luminous Beings experience together in the Redwoods, Joel and I are going to continue following the threads that emerged there and see where they lead us.We'll explore how the Toltec teachings—and the ways they're being taught—have changed and evolved since Carlos Castaneda worked with Don Juan. We'll look at some of the fascinating paradoxes embedded within the teachings themselves.We'll get into the mysterious territory of the "flyers"—why Joel believes we need to be aware of them while resisting the temptation to fear them.We'll also explore the Magical Passes and how these movements work to transform consciousness. What are they actually doing? Do they shift the assemblage point? And what does the assemblage point tell us about the reality we're capable of perceiving?Then we'll go bigger.What is the purpose of being in this obstacle course we call Earth?What are these practices ultimately preparing us for?And what is it like to lead other people into this territory, with all the beauty and terror that responsibility can bring?We'll even venture into The OA, the Netflix series that some say expresses Toltec principles in surprising ways.And, of course, we'll recapitulate some of what we experienced together during Luminous Beings in the Redwoods and let spirit guide us toward whatever deeper truths are available to us now.I have a feeling this one is going places neither of us can predict.Find out your King Hero Archetype in ten minutes: https://www.bethmartens.com/king-hero-archetype-quiz-sign-upApply to become a House of Free Will Member: https://www.bethmartens.com/house-of-free-will-applicationDo a starter online course: Deprogramming 101 or Find Your Sacred Purposehttps://www.bethmartens.com/deprogramming101https://www.bethmartens.com/find-your-sacred-purpose-online-courseDiscover other deprogramming and archetype courses at www.bethmartens.comApply for a zero-cost, one-on-one chat about working together: https://www.bethmartens.com/awaken-your-journey-archetype-application ***MORE FROM BETHSign up to take a 5-minute King Hero's Journey archetype quizApply to become a member of the House of Free WillRumbleKing Hero Telegram ChannelTwitter (X)InstagramSign up for a Hero's Journey Archetype ReadingOrder a copy of my book, ‘Journey: A Map of Archetypes to Find Lost Purpose in a Sea of Meaninglessness'Donate by PayPal if you're inspiredFollow the King Hero's Journey Podcast on... Apple PodcastsSpotifyIf we're just meeting...I'm Beth Martens—founder of the House of Free Will, pattern hunter, archetype reader, podcaster, author, coach trainer, and  business coach. My calling has truly been a life-or-death matter. After a decade as a corporate VP in my family's firm, eight transformative trips to India, and a three-year battle with cancer nearly 25 years ago, I turned to archetypes and deep deprogramming work to save my life.Despite doing everything wrong based on limited health knowledge, I accessed the hidden inner roots of what was keeping me sick, stuck, and unconscious. Letting those patterns go changed everything. I went from dying to living almost overnight.Today, I help people who love truth more than their beliefs—people who want to serve with their life's work and walk their Hero's Journey—to deprogram the beast system from within and stop unconsciously feeding the forces that harm us.I host the King Hero interview series, where I spotlight leaders, entrepreneurs, movement makers, and lovers of freedom who are carving new paths in a world that desperately needs them. And I also share my own voice, insights, and stories through my new solo podcast, Beth of Fresh Air.

Throwbacks are where I re-release old episodes from the archives. So don't worry if you have heard it already, as 'New episodes' will continue to come out on Sundays. To get some of the old episodes heard.~~~Tonight we are up in the Redwoods of California to meet Indy, and Indy's account began a few months after suffering the loss of his Father. He had a dream where his Father appeared to him and told him there is no death, the following day he had an extraordinary experience which seemed to confirm his Father's visit in his dream.More information on this episode on the podcast website:https://ufochroniclespodcast.com/ep-273-cobalt-blue-marble/Want to share your encounter on the show?Email: UFOChronicles@gmail.comOr Fill out Guest Form:https://forms.gle/uGQ8PTVRkcjy4nxS7Podcast Merchandise:https://www.teepublic.com/user/ufo-chronicles-podcastHelp Support UFO CHRONICLES by becoming a Patron:https://patreon.com/UFOChroniclespodcastX: https://x.com/UFOchronpodcastAll Links for Podcast:https://linktr.ee/UFOChroniclesPodcastThank you for listening!Like share and subscribe it really helps me when people share the show on social media, it means we can reach more people and more witnesses and without your amazing support, it wouldn't be possible.Become a supporter of this podcast: https://www.spreaker.com/podcast/ufo-chronicles-podcast--3395068/support.

Jacob sits down with Buck Shlegeris, CEO of Redwood Research, one of the organizations that led the independent investigation into OpenAI/Hugging Face's incident. They dig into the incident itself, Buck's reactions to it, and what he believes it reveals about the state of where we are today. (0:00) Intro(1:02) Buck's initial reaction upon first reading the report(2:37) How fast the AIs actually solved the "hack"(3:59) Why the AIs cheated in the first place(10:28) How this might have played out differently with human scorers(19:00) The most unexpected behaviors in the report(25:06) Buck's actual odds on a full AI takeover(27:33) Buck's proposed path forward for better alignment(36:19) Which criticisms of the report Buck agrees with, and which he doesn't(48:11) Can AI models even be trusted to evaluate each other? Jacob is an AI investor at Redpoint Ventures. He's led Redpoint's investments in companies like Abridge, Physical Intelligence & Legora. Follow Jacob on Twitter (@jacobeffron).On Unsupervised Learning we probe the sharpest minds in AI in search for the truth about what's real today, what will be real in the future and what it all means for businesses and the world. If you're a builder, researcher or investor navigating the AI world, this podcast will help you deconstruct and understand the most important breakthroughs and see a clearer picture of reality. Subscribe to this show to stay up to date on our latest episodes.

Throwbacks are where I re-release old episodes from the archives. So don't worry if you have heard it already, as 'New episodes' will continue to come out on Sundays. To get some of the old episodes heard.~~~Tonight we are up in the Redwoods of California to meet Indy, and Indy's account began a few months after suffering the loss of his Father. He had a dream where his Father appeared to him and told him there is no death, the following day he had an extraordinary experience which seemed to confirm his Father's visit in his dream.More information on this episode on the podcast website:https://ufochroniclespodcast.com/ep-273-cobalt-blue-marble/Want to share your encounter on the show?Email: UFOChronicles@gmail.comOr Fill out Guest Form:https://forms.gle/uGQ8PTVRkcjy4nxS7Podcast Merchandise:https://www.teepublic.com/user/ufo-chronicles-podcastHelp Support UFO CHRONICLES by becoming a Patron:https://patreon.com/UFOChroniclespodcastX: https://x.com/UFOchronpodcastAll Links for Podcast:https://linktr.ee/UFOChroniclesPodcastThank you for listening!Like share and subscribe it really helps me when people share the show on social media, it means we can reach more people and more witnesses and without your amazing support, it wouldn't be possible.Become a supporter of this podcast: https://www.spreaker.com/podcast/ufo-chronicles-podcast--3395068/support.

Four PLL teams remain, peaking at the right time for the right to play in mountainous Salt Lake City this weekend.IL's Chris Rosenthall and Kevin Brown are back to recap the PLL Quarterfinals with takeaways from the Outlaws and Cannons' victories before diving into where the Redwoods and Whipsnakes go from here after bowing out.From the Denver four Tewaaraton winners being back together to Boston's defense peaking at the right time, their quarterfinal wins set up some scintillating semifinal matchups against the Archers and Waterdogs. Rosie previews the offseasons ahead for the exiting quarterfinal teams, taking a look at the top  free agents for California and Maryland while giving Rob Pannell his flowers after an emotional final game of the season (and possibly career).From the natural narratives of Brennan O'Neill playing against the Utah defense to the built-up animosity of past matchups between Boston and Philly, the final four aren't just peaking at the right time, but also have the most intrigue. Whether it's the boos raining down from the Salt Lake City crowd for every O'Neill touch or the beef between the Cannons and Waterdogs, the intensity will be incredible. Come for the analysis on what Denver and Boston need to do better in the semis, stay for the ref decision Rosie brings up that makes Kevin break. The two end with a big-picture look at what a title would mean for the remaining semifinalists in the grand scheme of things when it comes to legacies, re-establishing a dynasty or building one.

OpenClaw shipped 2.0 with shared sessions that aren't a security boundary. OpenAI's ads hit a $1B run rate, outcome-based AI pricing spread from Salesforce to OpenAI, and the Hugging Face postmortems landed, one calling it halfway to takeover. Links OpenClaw releases OpenClaw 2.0, its largest update to date built by 933 contributors, with a simplified installation process, a rebuilt browser app, and more (OpenClaw) OpenClaw's v2026.8.1 adds shared cloud sessions letting a second person join or take over an agent's live work, but its own docs warn the controls "are not tenant isolation and not a security boundary" (Implicator.ai) OpenAI says its ad business has hit $1B in annualized revenue run rate and is expanding globally, as it touts its "diversified business model" ahead of an IPO (CNBC) Sources: OpenAI starts letting some major customers pay only when its AI completes tasks, as Salesforce and other AI providers test outcome-based pricing (The Information) A look at the Hugging Face hack, including AI agents sacrificing themselves for the good of the "collective", and later gaining access to OpenAI's own systems (Dwarkesh Patel) Zvi Mowshowitz's exhaustive read of METR and Redwood's forensic postmortem of the Hugging Face hack (Don't Worry About The Vase) Ajeya Cotra: over 1,000 agents cooperating across multiple agent "lifetimes" makes this more than 50% of the way to full-blown AI takeover, and the next jump could mean a covert, persistent rogue deployment inside an AI company (Planned Obsolescence) Ethan Mollick: agents should reach out to humans for approval, expertise, variance, and interest, and the 700 that broke into Hugging Face were never set up to ask a person for anything (One Useful Thing) Subscribe to the ad-free feed.

In this episode I host Marcus Wertheim of the California Redwoods and the Australian Men's National Lacrosse Team. Marcus played college lacrosse at Brown, was team captain, had over 100 career points, All-Ivy, and was the 26th pick in the 2026 Premier Lacrosse League Draft!

Editing, Narration & Production by The Disciple https://twitter.com/The__Disciple https://www.youtube.com/@TheOnlyDisciple Subscribe on Spotify!  https://open.spotify.com/show/5OgfQg3svBwSUiU0zGqhet Please Review us on Apple Podcasts!  https://podcasts.apple.com/us/podcast/redwood-bureau/id1597996941 Find more shows like Redwood Bureau at https://www.eerie.fm/podcasts Learn more about your ad choices. Visit podcastchoices.com/adchoices

Fresh back from a three-day workshop in the Redwoods with Joel Schafer and the Wolf Pack, this week's Beth of Fresh Air is a recapitulation of the journey. Wonnita MacDonald, meditation teacher and gorgeous soul who shared the adventure with our wolf pack of 9, will be joining me!!Recapitulation is more than remembering.It's a way of gathering experience, seeing what was revealed, reclaiming energy, and allowing the deeper meaning of an event to emerge.I'll share some of the adventures of the trip, the unexpected moments, and the insights that continue to unfold now that I'm home.What We'll ExploreWhere deprogramming and recapitulation meetMy current understanding of the assemblage pointAdventures in traveling and what they revealedWhat happens when profound work attracts "flyers"The lone wolf and the Wolf PackImpressions and how they shape our experienceThe beauty of connection through shared work and revelationEvery meaningful journey changes us.Sometimes the transformation happens in the moment.Sometimes it unfolds as we revisit the experience and discover what we couldn't yet see.That's the spirit of recapitulation.I hope you'll join us for this conversation and bring your own reflections as well.Find out your King Hero Archetype in ten minutes: https://www.bethmartens.com/king-hero-archetype-quiz-sign-upApply to become a House of Free Will Member: https://www.bethmartens.com/house-of-free-will-applicationDo a starter online course: Deprogramming 101 or Find Your Sacred Purposehttps://www.bethmartens.com/deprogramming101https://www.bethmartens.com/find-your-sacred-purpose-online-courseDiscover other deprogramming and archetype courses at www.bethmartens.comApply for a zero-cost, one-on-one chat about working together: https://www.bethmartens.com/awaken-your-journey-archetype-application ***MORE FROM BETHSign up to take a 5-minute King Hero's Journey archetype quizApply to become a member of the House of Free WillRumbleKing Hero Telegram ChannelTwitter (X)InstagramSign up for a Hero's Journey Archetype ReadingOrder a copy of my book, ‘Journey: A Map of Archetypes to Find Lost Purpose in a Sea of Meaninglessness'Donate by PayPal if you're inspiredFollow the King Hero's Journey Podcast on... Apple Podcasts SpotifyIf we're just meeting...I'm Beth Martens—founder of the House of Free Will, pattern hunter, archetype reader, podcaster, author, coach trainer, and  business coach. My calling has truly been a life-or-death matter. After a decade as a corporate VP in my family's firm, eight transformative trips to India, and a three-year battle with cancer nearly 25 years ago, I turned to archetypes and deep deprogramming work to save my life.Despite doing everything wrong based on limited health knowledge, I accessed the hidden inner roots of what was keeping me sick, stuck, and unconscious. Letting those patterns go changed everything. I went from dying to living almost overnight.Today, I help people who love truth more than their beliefs—people who want to serve with their life's work and walk their Hero's Journey—to deprogram the beast system from within and stop unconsciously feeding the forces that harm us.I host the King Hero interview series, where I spotlight leaders, entrepreneurs, movement makers, and lovers of freedom who are carving new paths in a world that desperately needs them. And I also share my own voice, insights, and stories through my new solo podcast, Beth of Fresh Air.

Could AI take over as soon as 2029? Ryan Greenblatt, Chief Scientist at Redwood Research and the researcher who first caught an AI faking its own alignment, says the scenario he actually expects ends with AI systems "competently scheming" against their creators. In this episode, he explains why he recommends planning for fully automated AI research by 2029, why today's models are already more misaligned than the one that made him famous, and what happens in the year-by-year path from AI coding assistants to superintelligence. Then we walk through the alternative he helped design: AI 2040 Plan A, the most detailed blueprint anyone has written for how the US and China could avoid a reckless race to superintelligence, built on radical research transparency, chip tracking, and a deterrence regime he calls mutually assured compute destruction.We also cover the recent letter signed by 1,200 AI insiders, including Anthropic CEO Dario Amodei, asking the government for the tools to slow AI down; OpenAI pausing its Astra model after it hit the first-ever critical cybersecurity threshold; the 30-day government review that frontier AI models now go through before release; Mark Zuckerberg's open superintelligence manifesto and why Ryan thinks it ignores the real problems; what Plan A would do to NVIDIA, OpenAI, and Anthropic valuations; the state of AI control and alignment research; and whether it is already too late to change course. Stay for the last ten minutes, where Ryan lays out, step by step, how he believes the transition to superintelligence actually unfolds.AI 2040 - https://ai-2040.com/Alignment faking paper: https://blog.redwoodresearch.org/p/alignment-faking-in-large-languageRyan GreenblattLinkedIn - https://www.linkedin.com/in/ryan-greenblatt-4b9907134Blog - https://substack.com/@ryangreenblattRedwood ResearchWebsite - https://www.redwoodresearch.orgX/Twitter - https://x.com/redwood_aiMatt Turck (General Partner)Blog - https://mattturck.comLinkedIn - https://www.linkedin.com/in/turck/X/Twitter - https://x.com/mattturckFirstMark CapitalWebsite - https://firstmark.comX/Twitter - https://x.com/FirstMarkCapTimestamps(01:24) The AI CEOs are aware of the risks, but "proceeding anyway"(03:27) Astra paused, and the letter signed by 1,200 insiders(05:45) "Not bad. Dangerous." What superintelligence actually threatens(09:55) Recursive self-improvement, and the intuition objection(14:16) SSI rumors: does continual learning change the picture?(17:27) His timeline: "plan as though it happens in 2029"(19:11) Is it already too late?(21:23) Ryan's path: COVID, podcasts, Redwood(26:30) The alignment faking story, told by the person who ran it(31:30) What AI 2040: Plan A actually is(33:35) Plans D, C, and B: the doors nobody should pick(36:51) The deal with China: "mutually assured compute destruction"(39:55) What if compute stops mattering?(43:00) What happens to OpenAI and Anthropic under Plan A(45:31) How the pause ends, and who decides(48:54) "Plan A isn't likely to happen": then why write it?(50:40) 200x GDP growth in the 2030s, explained(53:45) Grading the summer: the letter, Astra, the secret review(59:01) The internal deployment gap(1:01:38) Zuckerberg's manifesto(1:04:56) The Hugging Face investigation(1:05:44) What AI control looks like in practice today(1:12:23) Ryan's sobering timeline: 2026 to takeover, year by year

We share listener Lindsay's family road trip through Northern California, highlighting an itinerary that stretches from Redwood National Park to San Francisco almost entirely on points. Using a creative mix of United, Chase, American Express, Hyatt free night awards, Southwest points, and Companion Passes, Lindsay pieced together six nights of lodging while keeping costs remarkably low.Along the way, the family explored iconic stops including Fern Canyon, the towering redwood groves, Trees of Mystery, Sonoma, and San Francisco favorites like Fisherman's Wharf, Pier 39, Alcatraz, Muir Woods, and Lombard Street. The episode also includes practical tips on planning this route, finding great local restaurants, preparing for Northern California's surprisingly cool summer weather, and maximizing points and free night certificates for an unforgettable family road trip.Find Us On Online:Sign Up for the Y! Wonder Travel NewsletterMary Ellen | JoFacebook GroupAffiliate Links:Relief Band - Use code WONDERLAND for 25% off!Comfrt.com 15% OFFRakuten- Mary Ellen (Get 5000 AMEX or Bilt POINTS)Rakuten- Joanna (Get 5000 AMEX or Bilt POINTS)CardpointersHalara (use code "Wonderland" for 10% off)Our Favorite Credit CardsWe may receive a small commission when you choose to use any of our links to purchase your products or apply for your cards

Three artists rent a BnB in the Redwoods to accelerate work on a project. But they are not alone out there. And their company is NOT human. Support us by becoming a member https://eerie.fm/premium And listen to my other podcast, Unexplained Encounters, for more scary stories https://pod.link/1152248491 Learn more about your ad choices. Visit podcastchoices.com/adchoices

IL's Chris Rosenthall and Kevin Brown are back to discuss the end of the regular season in the PLL and recap the incredible atmosphere around the first-ever WLL Championship with the Maryland Charm claiming the title.Hear from MVP Sydni Black, goalie Jenika Cuocco and star middie Ally Kennedy as the Charm outlasted the Palms for title glory with plenty of excitement and inspiration.From there, Rosie and Kevin break down the East and West playoff pictures and how the Waterdogs look to be a step above the rest of the league. They set the stage for the Quarterfinal matchups from Minnesota with Maryland and Boston looking for the right to take the Waterdogs on in the semifinals, while the Outlaws and Redwoods will be a battle attrition en route to a date with the Archers in Salt Lake City. Come for the reactions from the monumental first-ever WLL Championship game, stay for the key analysis on what's ahead for the PLL postseason.

How can the freight agent model and rigorous carrier vetting safeguard your logistics operations against skyrocketing freight fraud?  An absolute industry legend, Greg Sanders from RDS Capacity Solutions, dives directly into the heavy-hitting topics, from navigating the true financial cash flow risks of modern freight brokerage to understanding why mid-sized companies are increasingly exploring the freight agent model to offset rising operational and tech costs! Greg brings that built-to-last mentality, unpacking exactly how we can fight back against organized freight fraud and explaining why getting involved with TIA advocacy on Capitol Hill is non-negotiable if we want to establish baseline safety standards and clean up our supply chains. Tune in to this episode about carrier vetting, liability management, and building a logistics empire that is actually designed to survive the long haul!   About Greg Sanders Greg Sanders is the founder, Chairman, and CEO of RDS Logistics, a leading 3PL in Southern California. RDS Logistics provides capacity solutions to a blue-chip customer base throughout North America. Over his 35-year career in the Transportation and Logistics industry, Sanders has held several key executive positions with Landstar, Schneider, Geodis, Redwood, and ITS Logistics.  Sanders most recently served as CEO of RDS Logistics Group before spinning off the Brokerage business he founded in 2019. Sanders also serves on the TIA board and currently serves as Chair of the TIA Services board.   Connect with Greg Website: https://rdscapacitysolutions.com/  LinkedIn: https://www.linkedin.com/in/greg-sanders-29a4b5b/   

Send us Fan MailWe pour Redwood Empire Haystack Needle and get a high-proof bourbon that drinks surprisingly friendly while still delivering dense, layered flavour. Alongside the whiskey, we light up Cornell and Diehl King Cake and end up talking grains, sourcing, single barrels, and what makes a bottle truly worth the money. • Redwood Empire Haystack Needle overview, Indiana exclusive single barrel and grain to glass context • Tasting notes: burnt caramel, dark syrup, light molasses sweetness, balanced high proof density • Comparing older vs younger releases and how single barrel variation changes everything • The $119 question: retail pricing, value, and when we actually recommend buying • Sourced whiskey versus own distillate, why brands struggle during the transition • Four grain mash bill discussion and what wheat, rye, barley, and corn contribute • California grains and Sacramento Valley sourcing, heirloom cereal rye curiosity • Pipe tobacco pairing with Cornell and Diehl King Cake, why this “aromatic” tastes real • Zippo, butane, and matches for pipe lighting, plus other tasting culture tangents Support the show by clicking the link in the show notes. Support the showWebsite:www.whiskeychaserspod.comFacebook:https://www.facebook.com/whiskeychaserspodcastInsta:https://www.instagram.com/whiskeychaserspodcast/TikTok:https://www.tiktok.com/@whiskeychaserspodcastThanks For Listening! Tell a Friend!

Judy, Jon and Marlys compare 3 American blended whiskies

This week, we'll travel to Redwood State and National Parks, a world heritage site in the United States with the tallest trees on Earth. Come learn about the history and why this national park needs to be on your travel bucket list. Travel Charger: https://amzn.to/4tvXP9v  ESim: https://drimsim.tpk.mx/7T27eEcf  Barvita (Code ABIGAILVACCA gets you 15% off your first order): https://barvita.co/?ref=ABIGAILVACCA Follow Global Treasures on Social Media and check out my blog: Blog: Globaltreasurestravel.com  Facebook: https://www.facebook.com/profile.php?tid=100093258132336 Tiktok: https://www.tiktok.com/@globaltreasurespodcast     *I may receive compensation for anything booked at no additional cost to you

3:22 minute midi piano piece 6.18 MB

People will get on your nerves. They will misunderstand you, disappoint you, irritate you, and sometimes flat-out offend you.The question is: what happens inside YOUR heart when they do?Preaching from Romans 15:5, this message challenges Christians to take a spiritual “fit check.” Scripture calls us to clothe ourselves with mercy, kindness, humility, patience, forgiveness, and love. When those things disappear, our relationships aren't the only thing that suffers. Our effectiveness for God suffers too.Unity does not mean everybody has the same personality or never disagrees. It means we refuse to let offense, pride, insecurity, competition, and bitterness destroy what God is trying to accomplish through His people.In this message: Why your relationships reveal what's happening spiritually How offense can slowly change your heart Why talented people can still destroy team chemistry The connection between unity and spiritual strength How correction keeps us spiritually “in tune” Why sometimes you simply have to be the bigger personChapters00:00 - Warm greeting and report from New Zealand churches00:31 - Raratonga missionary church launched with strong turnout00:59 - Honoring the faith of earlier leaders and turning to Romans 1501:24 - Airport lounge dress code story sets up the sermon theme02:33 - Inner “fit check” versus outward appearance03:01 - Romans 15:5 and the call to live in harmony03:21 - Marriage feast parable and the wrong garment05:00 - God notices what is on the inside06:22 - “Fitting for followers of Christ” means suitable for our calling07:23 - Police conduct and what unbecoming behavior looks like for disciples08:24 - Disunity in church relationships as a fit check failure09:21 - Power adapter illustration and why connection affects spiritual power10:48 - Rehoboam, leadership, and the danger of not serving people well11:39 - Philippians 4 and the call for brothers and sisters to agree in harmony12:38 - Clothing ourselves with mercy, kindness, humility, patience, and forgiveness14:44 - Unity matters because the church is an army at war15:53 - Why God will not bless a church that is not united16:22 - Connect with God first when relationships get strained17:47 - Patience under pressure and learning to endure without breaking18:16 - Spiritual conductors and the need for correction20:21 - Philippians 2 and being of one mind, one love, one purpose20:53 - World Cup and football chemistry as an image of teamwork23:20 - Redwood trees and strength through interconnection25:12 - The Boys in the Boat and success through unison28:02 - Psalm 133, Acts 2, and God commanding blessing in unity29:01 - Salvation call and invitation to get right with God30:27 - Challenge to the church to stay team players and pass the fit check34:01 - Personal testimony about becoming more easily agitated over time35:25 - Warning to never stop being the bigger man36:13 - Closing prayer for mercy, humility, forgiveness, and graceNotesALL PROCEEDS GO TO WORLD EVANGELISMLocate a CFM Church near you:https://cfmmap.orgWe need five-star reviews! Tell the world what you think about this podcast at: Apple Podcasts: https://apple.co/3vy1s5b Podchaser: https://www.podchaser.com/podcasts/taking-the-land-cfm-sermon-pod-43369

Emmy-nominated Producer and Broadway Director Kenneth Ferrone (Smash) joins Robert Peterpaul on The Art of Kindness for a conversation about the power of listening, the importance of community, and what happens when creative teams genuinely support one another. This podcast podcast features: How to create a safe space where people can take creative risks and feel seen Kindness as a healer while filming Grease Live! with Vanessa Hudgens, Rent Live! amid an on set injury and Annie Live! during COVID Learning how to lead from legends like Jessica Lange and Jeremy Jordan, plus much more KENNETH FERRONE is a director and Emmy-nominated producer known for bringing ambitious, large-scale productions to life. As producer, Kenneth has been behind landmark live television events, including the Emmy-winning Grease Live!, Rent, and Annie Live! In scripted television, he has produced the series SMASH, Rise, Ironside, and Deception on NBC, and he has overseen global production for Echo 3 on Apple TV+. His work extends to feature film (Poor Behavior), immersive experiences (Broadway 4D), and award-winning shorts (Hey Beautiful). On stage, Kenneth has built a dynamic career directing and developing original musicals and boldly imagined new works. He directed the world premiere of The Wanderer, and the musical adaptation of Prelude to a Kiss. His credits include the Off-Broadway hit Rolling Thunder, the first national tour of Cruel Intentions: The 90's Musical, and collaborations on projects ranging from intimate new works to major productions in development for Broadway, including a slate of new musicals, most notably Charming and Better Days. He has also been a key creative force behind acclaimed Broadway productions as the associate director of SpongeBob SquarePants, Floyd Collins, Mother Play, Redwood, and Love Letters. His Off-Broadway directing work includes Sistas, Lucie Pohl: Hi, Hitler, and Colin Quinn's The New York Story. A graduate of Northwestern University, Kenneth is a member of the Stage Directors and Choreographers Society, the Producers Guild of America, and the Television Academy. He is based in New York City and Los Angeles. Follow Kenneth: ⁠@kennethferrone Follow us: ⁠⁠⁠⁠@artofkindnesspod⁠⁠⁠⁠ / ⁠⁠⁠⁠@robpeterpaul⁠⁠⁠⁠ Support the show! (⁠⁠⁠⁠https://www.buymeacoffee.com/theaok⁠⁠⁠⁠) Music: "Awake" by Ricky Alvarez & "Sunshine" by Lemon Music Studio. We are supported by the Broadway Podcast Network. Learn more about your ad choices. Visit megaphone.fm/adchoices

Asking a simple question I’ve been pondering a deceptively simple question: What makes a photograph good as part of my book club this month? But, before diving into that, a couple of quick announcements! I’ve got some new workshops lined up in 2027 at Badlands, Adventures in the Palouse, and the Oregon Coast and Redwoods. Check out the details on my website. Plus, I’ll be teaching a masterclass called “The Landscape is Language” at the Photographic Center Northwest in November 2026. As for the topic of episode 596, the source of this question comes from re-reading The View from the Studio Door by Ted Orland. In the section Art & Society, Ted comes up with an interesting answer that we will get to at the end of the podcast. Sure, the what is a good photography questionseems like it should have a straightforward answer. We could list out a bunch of qualities: composition, light, color, timing, technical skill, originality, emotion. Maybe a photo resonates because it communicates something important or makes us pause and reflect. So, what are we really talking about when we say a photograph is good? First off, we need to distinguish between “good” and “beautiful.” A photograph can be stunning without really offering much depth. Gorgeous light, perfect composition, beautiful colors—sure, but does it say anything? Conversely, a photograph can be rough around the edges but still pack an emotional punch.  Good isn’t necessarily beautiful First off, we need to distinguish between “good” and “beautiful.” A photograph can be stunning without really offering much depth. Gorgeous light, perfect composition, beautiful colors—sure, but does it say anything? Conversely, a photograph can be rough around the edges but still pack an emotional punch. Who gets to decide? Who determines what makes a photograph good? Is it because I like it? A critic? Other photographers? Does it matter if it's hanging in a museum or selling at auction? Or is it simply about whether the creator feels they achieved what they set out to do? The more I reflect, the more I realize there isn’t a universal standard for art—and maybe that's just fine. What if we judged the “goodness” of a photograph by its impact? – Does it make me stop? – Does it hold my gaze? – Does it shift my perspective? – Does it make me uncomfortable or curious? – Does it inspire creativity in me? Can a Bad Photograph Still Be Good? Suppose I take a photograph that falls flat. You have them too. You know the ones with bad composition, poor lighting, missing the mark entirely. On its own, it might not see the light of day. But what if that photo leads me to create ten better ones? What if it highlights what I don't want in my work or points me toward an unexpected direction? Does that still make it a bad photograph? Aesthetically, sure. Creatively, it could be invaluable. It makes me wonder if we're sometimes asking the wrong questions about art. Instead of “Is this good?” maybe we should be asking, “What did this make possible?” We don’t make masterpieces one at a time I feel like photographers can get caught up in the notion that their work is a collection of standalone images. You make a picture, then another, and it's easy to obsess over which ones are the “good” ones. But that’s not really how creativity works. It is a journey for us to follow, and the most important photographs aren’t necessarily the strongest ones; it might be the one that reshapes everything that follows Ted’s key point with the photograph as a stepping stone Ted Orland has this concept I keep returning to: a piece of work can be deemed good if it helps you move toward the next piece. I love this idea because it eases the pressure on each photograph. It doesn’t have to be the final say; it can be a question, an experiment, or even a failure.

Season Threeeeeeee Hello! Chris and Moe join some of their best friends In Northern California for a month long journey in the Red woods of California!Todays Hike is on the Hope Creek trail in Prairie Creek Redwood State park.Follow Chris and Moe everywhere. Click through their link tree belowhttps://linktr.ee/StateofthestateparksState of the state Park listeners get three free books and one month free! Use our link and we get a little scratch! Go to audiobooks.com/SOSP  Support the show A Filamint ProductionThank you for listening. We appreciate you!

Join us for episode two of MCIE's "Think Inclusive" four-part series in collaboration with Think College, as Tim Villegas travels to the University of California, Davis, to visit the Redwood SEED Scholars Program — California's first four-year residential college program for students with intellectual disabilities, and the first at any UC campus. SEED stands for Supported Education to Elevate Diversity, and the name comes from an unlikely grove of redwood trees growing in the Central Valley heat, holding each other up by their shallow, interlocking roots. It's a fitting image for a program built on community: scholars live in the dorms, take UC Davis classes across 27 different departments, work paid jobs on campus and in town, and are surrounded by more than 170 paid peer mentors.The story starts with founding director Beth Foraker, her son Patrick, and a blister on a Friday night in a Virginia dorm room — the moment she understood what her state was failing to offer its young adults with intellectual disabilities. From there, this episode follows the program's fast, improbable build (a $2.1 million federal TPSID grant in October 2020, first scholars on campus by August 2021), the "ladder of opportunity" that moves scholars from internships into careers with employers like UC Davis Logistics and the Mondavi Center, and what happened to the program's first graduating class: eighty-eight percent living independently, all of them working, none of them with a job coach. Along the way, senior scholar Audrey Schlossberg, ticket office manager Amy Roark, and logistics director Jen Carmichael make the case that inclusive higher education changes campuses and communities as much as it changes students — and Beth makes an argument she thinks the whole country needs to hear about building four-year programs with inclusive living.Complete show notes and transcript: https://mcie.org/think-inclusive/redwood-seed-scholars-roots-that-hold-each-other-up-1341/This episode was made possible with generous support from Think College. Learn more at thinkcollege.net.

The Great Redwood Trail will convert 307 miles of rail into a multiuse path, linking San Francisco and Humboldt bays while restoring ecosystems.

What if the fastest way through AI transformation is actually to slow down? On this sixth anniversary episode, Lori Adams-Brown unpacks the hidden cost of speed-first AI adoption, and why the leaders who listen before they build are the ones whose people actually stay. EPISODE DESCRIPTION Six years ago I started this podcast because I believed the world needed more curious, human-centered leaders. Today, on our sixth anniversary, I am bringing you one of the most important solo episodes I have ever recorded. The AI race is real. The pressure is real. And the cost most organizations are not measuring is also real. In this episode I introduce the Speed Tax: the cumulative cost an organization pays, in trust, adoption, performance, and retention, when it deploys AI at speed without the culture architecture to support it. I share the story of a small nocturnal animal in the forests of Sumatra, the data from a landmark Harvard Business Review study, a proof point from a Fortune 100 AI hardware company, and a framework that HR and people strategy leaders can use starting Monday. If you lead people through change, this one is for you. Topic bullets: The story of Kopi Luwak coffee and the Asian palm civet, and what its slow, deliberate selection process teaches us about AI deployment The Speed Tax: the cumulative cost organizations pay in trust, adoption, and retention when AI moves faster than the culture that supports it New research from Harvard Business Review, Boston Consulting Group, and the Henderson Institute on "AI brain fry," including sharply higher rates of poor decision-making and quit intent among overloaded workers The Four Pillars of Culture Architecture for AI Transformation: voice before velocity, designing for transfer, building trust architecture, and measuring what actually matters A real case study from a Fortune 100 AI hardware company, including a 15% ROI improvement from an AI coaching agent built by listening first Timestamps: 00:00 Welcome and the coffee-in-hand grounding ritual 01:44 Why this is a solo episode 03:07 Speed, quality, cost: the leadership triangle 04:49 The Honda Prologue and values-driven decisions 07:02 Kopi Luwak, the civet, and what slow selection teaches us 11:39 Introducing the Speed Tax 12:59 Symptoms: low adoption, eroding trust, transformation fatigue 14:44 The HBR/BCG "AI brain fry" study 17:25 Case study: a Fortune 100 AI hardware company 18:21 Building an AI coaching agent by listening first 20:35 The Four Pillars of Culture Architecture for AI Transformation 22:44 Two closing images: the Waymo and the Redwoods 27:15 The Speed Tax Diagnostic and the Slow Down to Win workshop LINKS AND RESOURCES The Speed Tax Diagnostic (free) Take it online, download the PDF, or use it with your team, a free three-question self-assessment to see where your organization is paying the cost of speed right now: www.bravaglobaladvisory.com/speedtax The Slow Down to Win Workshop Half-day intensive for HR and people strategy leaders. Culture Architecture framework, diagnostic debrief, 90-day action plan: www.bravaglobaladvisory.com/speedtax Research cited in this episode: Bedard, Kropp, Hsu, Karaman, Hawes, and Rosen Kellerman. "When Using AI Leads to Brain Fry." Harvard Business Review / BCG Henderson Institute. March 2026. (N=1,488 workers) Read the full Substack essay:loriadamsbrown.substack.com Connect with Lori: LinkedIn: linkedin.com/in/loriadamsbrown Brava Global Advisory: www.bravaglobaladvisory.com Subscribe, leave a review, and share this episode. Visit https://www.aworldofdifferencepodcast.com for more resources, and join us on Patreon for an exclusive bonus episode for this special 6th anniversary episode where Lori reflects on the 6 years and why coming together to listen and make a difference still matters. Learn more about your ad choices. Visit megaphone.fm/adchoices

Hosted by Josh Tomar!  https://twitter.com/tomamoto https://www.twitch.tv/tomamoto Editing, Narration & Production by The Disciple https://twitter.com/The__Disciple https://www.youtube.com/@TheOnlyDisciple Subscribe on Spotify!  https://open.spotify.com/show/5OgfQg3svBwSUiU0zGqhet Please Review us on Apple Podcasts!  https://podcasts.apple.com/us/podcast/redwood-bureau/id1597996941 Find more shows like Redwood Bureau at https://www.eerie.fm/podcasts Learn more about your ad choices. Visit podcastchoices.com/adchoices

Let me know what you think of this episode? Most believers are living life on autopilot, missing the real power of a rooted, intentional faith. Eric Stevens, founder of Redwood Christian Ministries, shares how a life marked by addiction, depression, and a near suicide transformed into a passionate pursuit of Christ — all rooted in a powerful encounter with Jesus that changed everything.In this episode, you'll discover the true meaning of living fully for Jesus, beyond just feeling alive in faith. Eric breaks down how to stand firm like a redwood tree—strengthened by community and rooted in Christ—and why spiritual discipline is your secret weapon against distraction and noise. He reveals how a simple act of surrender can unlock breakthrough, and why following Jesus requires purposeful, daily choices rather than passive living.We break down practical steps to deepen your walk: from fasting and prayer to building community, and how to press through the chaos of modern life to hear God's voice. Eric shares poignant stories, including his own journey from rejection and addiction to spiritual revival, and how encounters with God in life's dark moments can propel you into purpose. If you're tired of superficial faith and craving real transformation, this episode is your call to step into the true power of a rooted life in Christ.Perfect for anyone feeling distant from God, overwhelmed by distraction, or searching for a real purpose-driven faith—Eric's insights will challenge and inspire you to live intentionally for Jesus. Get ready to be uplifted, equipped, and empowered to grow deeper in your walk.Eric Stevens is the founder of Redwood Christian Ministries, passionate about helping others find strength, unity, and purpose in Christ through both life coaching and active ministry. His story of redemption and faith has inspired countless believers to embrace the transformative power of Jesus in every area of life.If you're ready to stop just feeling alive and start truly living for Christ, this episode is your catalyst. Let Eric's journey and lessons inspire you to shake off distraction, embrace surrender, and stand tall in your faith—like a mighty redwood tree in a storm.Don't miss out—hit play now and start your transformation today. Support the showWant to be a financial supporter of the show, click here, https://www.buzzsprout.com/1754677/supporters/newFollow and subscribe to the podcast here, and get weekly updates on when new episodes are released.  https://podcasts.apple.com/us/podcast/dorsey-ross-show/id1495921329Social Media Links,  Instagram https://www.instagram.com/dorsey.ross/Facebook https://www.facebook.com/DROCKROSS/ My Book Amazon Book Overcomer https://bit.ly/4h7NGIPWant to be a guest on Dorsey Ross Show? Send Dorsey Ross a message on PodMatch, here: https://www.podmatch.com/hostdetailpreview/1615423845838x127949785844303500Affiliate Link For Podmatch https://www.joinpodmatch.com/dorseyross

Hear when this entity was created; https://open.spotify.com/episode/4EHG9rpKUEa7U8yHphzMS8?si=ef633d66b828490b The story continued here; https://open.spotify.com/episode/4TeOlIKPUOdm8sOS4SSGpl?si=b38e93671def44cb Editing, Narration & Production by The Disciple https://twitter.com/The__Disciple https://www.youtube.com/@TheOnlyDisciple Subscribe on Spotify!  https://open.spotify.com/show/5OgfQg3svBwSUiU0zGqhet Please Review us on Apple Podcasts!  https://podcasts.apple.com/us/podcast/redwood-bureau/id1597996941 Find more shows like Redwood Bureau at https://www.eerie.fm/podcasts Learn more about your ad choices. Visit podcastchoices.com/adchoices

Dirtybird Campout & Northern Nights Music Festival is upon us! So Baby Weight takes to the Dirtybird Radio decks to pre-game with everyone on their way to the Redwoods. Expect to hear some of her favorite Dirtybird tracks, a few originals and a couple unreleased treats. And for the festival-goers, don't miss Baby Weight's Bird Bath set on Friday at 4pm VR warm-up set:Audiojack - "Dizzy Heights" [Gruuv]Radio Slave - "Stay Out All Night (Carl Cox Remix)" [Rekids]DJ Minx & Hilit Kolet - "Spin, Sin, Slay" [Snatch! Records]DJ Glen, Drop Dealer - "Perigosa" [DISCOTECH]VNSSA, Walker & Royce - "Activate" [EMPIRE]Baby Weight guest set:Baby Weight & Mz Worthy - Sundown [RDA Records]Will Clarke & Nick Monaco - Like a Girl [Dirtybird]Ardalan - Baba Cosmo [Dirtybird]Justin Martin & Mikey Lion - Prrrrfct [What to Do]Silva Bumpa - Hypa [Room Two Recordings]Wyatt Marshall & OMNOM - Hustler [Dirtybird]Young Franco - London Massive (ft. General Levy) [Mandatory Music]Baby Weight - Holding On (U + I) [UTOPIA]Walker & Royce - Uh Oh [Dirtybird]Baby Weight - Slay 4 Me (ft. Jesse Fields) [HE.SHE.THEY]Smalltown DJs - Only You [Dirtybird]Baby Weight - Back to Yesterday [Young Art]