Podcasts about railways

Welcome back sleepy listeners!  Tonight we will continue with Chapter 2 from the beloved classic, "The Railway Children" by E. Nesbit. So go ahead and settle in, close your eyes, and let the soothing narration transport you to a world of wonder and timeless enchantment. Sweet dreams dear listeners!JoanneMusic in this episode is 'Freeform' by Rannar Sillard via Epidemic SoundThis podcast is 100% listener-supported, completely ad-free, and made possible by wonderful listeners like you. Thank you for helping me keep bedtime a peaceful place.If you'd simply like to make a one-time contribution to help support the podcast, you can do so here: https://driftoff.supercast.com/donations/new. Every gift, no matter the size, is deeply appreciated and helps me continue creating peaceful stories for you.If you'd like even more relaxing stories throughout the week, Drift Off Premium includes:• Fresh new premium episodes every Tuesday & Thursday• Instant access to the complete premium archive• Intro-free listening so you can dive straight into your wind down• Listen first, months—or even years—before the public feed• An exclusive full-length audiobook libraryYou can learn more by visiting www.driftoffpodcast.com, where you'll also find my downloadable audiobooks, my Dream Shop, and everything else happening in the world of Drift Off. Thank you for being here, and for helping keep Drift Off a peaceful, ad-free space. 

Celebrating classic television and radio, as well as looking ahead to what's on the telly now and later.

Celebrating classic television and radio, as well as looking ahead to what's on the telly now and later.

Celebrating classic television and radio, as well as looking ahead to what's on the telly now and later.

Celebrating classic television and radio, as well as looking ahead to what's on the telly now and later.

Celebrating classic television and radio, as well as looking ahead to what's on the telly now and later.

Celebrating classic television and radio, as well as looking ahead to what's on the telly now and later.

Celebrating classic television and radio, as well as looking ahead to what's on the telly now and later.

Celebrating classic television and radio, as well as looking ahead to what's on the telly now and later.

Celebrating classic television and radio, as well as looking ahead to what's on the telly now and later.

Celebrating classic television and radio, as well as looking ahead to what's on the telly now and later.

Celebrating classic television and radio, as well as looking ahead to what's on the telly now and later.

Celebrating classic television and radio, as well as looking ahead to what's on the telly now and later.

Celebrating classic television and radio, as well as looking ahead to what's on the telly now and later.

Celebrating classic television and radio, as well as looking ahead to what's on the telly now and later.

Celebrating classic television and radio, as well as looking ahead to what's on the telly now and later.

Mark is in Forres to meet up with naturalist and educator Dan Puplett. Dan's been running bird language courses, helping people understand what birds are really saying and how to interpret their different calls.Ardersier Common has officially become the Highlands' newest Local Nature Reserve after more than two decades of conservation work. Home to the rare small blue butterfly and one of the UK's rarest orchids, Phil Sime and Morven Livingstone joined High Life Highland countryside ranger John Orr to explore this remarkable wildlife haven for this week's Scotland's Outdoors PodcastDiseased trees in Callendar Park are set to be removed to protect the nearby Antonine Wall, part of a UNESCO World Heritage Site. Experts say the work is needed to safeguard the Roman monument, built almost 2,000 years ago. Rachel joined Falkirk Council Greenspace Team Leader Mike Ewart to hear why the work is so important.Also, in Callendar Park, plans are taking shape to honour one of the 20th century's greatest plant hunters. Falkirk-born George Forrest travelled extensively in China, collecting thousands of plant specimens, many of which are familiar in gardens today. Rachel and Mike Ewart are joined by Leonie Paterson from the Royal Botanic Garden Edinburgh to learn more about one of Scotland's most celebrated botanists.We love talking about the benefits of spending time outdoors on this programme, and few people believe in its healing power more than Pete Crane. A former Cairngorms National Park Authority employee, Pete became seriously ill a few years ago. Rachel met him in Nethy Bridge to hear how the outdoors helped him on his road to recovery.After an absence of several years, a familiar landmark has returned to the waterfront at Port Glasgow. The newest replica of The Comet, Europe's first seagoing commercial paddle steamer, is once again a feature of the shoreline. Celebrating a story that helped shape the town's proud shipbuilding heritage, Paul English has been finding out more from local councillor Chris Curley.Mark heads to the banks of Loch Lomond to explore the East Loch Lomond Path, the only Scottish route nominated in The Ramblers' Britain's Favourite Path 2026 competition. The rugged stretch along the eastern shore is part of the iconic West Highland Way, and Danny Carden from Ramblers Scotland explains why it deserves your vote.And the Aberdeenshire village of Maud was once a thriving railway junction. While the station and railway closed many years ago, the former station now lives on as a museum. Mark paid a visit and even got the chance to ride one of its most popular attractions, a miniature railway that takes visitors on a short but memorable journey.

North Macedonia has waited 21 years at the EU's door. Zoran Dimitrovski and Linas Kojala ask what delay now costs Europe. Look at a map and the unresolved logic is striking. Albania, Bosnia and Herzegovina, Kosovo, Montenegro, North Macedonia and Serbia are almost entirely surrounded by EU and NATO members. These countries are not on some distant European frontier. They form an enclave within the Union's own geography. In 2003, at the Thessaloniki summit, the EU promised the Western Balkans a European future. More than two decades later, Croatia remains the last country to have joined, back in 2013. Since Russia's invasion of Ukraine, enlargement has shifted from a slow technical process to an urgent geopolitical question: what happens when Europe leaves a space inside its own borders unfilled? My guests brought two unusually powerful perspectives to that question. Zoran Dimitrovski, North Macedonia's Deputy Minister of Foreign Affairs and Foreign Trade, spent 35 years as a journalist before entering government. He edited some of his country's leading newspapers, reported from Washington, wrote more than 1,500 articles and investigations, and continues to teach critical thinking and analytical writing. Alongside him was Linas Kojala, CEO of the Geopolitics and Security Studies Center in Vilnius and a lecturer at Vilnius University. A Fulbright scholar with studies at Oxford, Cambridge and Harvard, Kojala has written about Lithuania's own journey into the European Union and has been ranked among his country's most influential public figures. Twenty-one years at the front door North Macedonia became an EU candidate in 2005, around the same time as Croatia. Yet it still has not opened substantive accession negotiations. The country first faced a long dispute with Greece over its name, eventually resolved through the Prespa Agreement and the adoption of the name North Macedonia. That opened the way into NATO. A second dispute then emerged with neighbouring Bulgaria, involving language, identity, history and the recognition of a Bulgarian community within North Macedonia's constitution. Zoran Dimitrovski did not deny the work still required within his own country. North Macedonia must continue aligning its laws with the EU, strengthening the judiciary and fighting corruption. His argument was that these shortcomings were not the principal reason the country had been stopped. This describes one of the demands that, in Dimitrovski's view, reach beyond the Copenhagen criteria governing democratic institutions, human rights, the rule of law and a functioning market economy. There is, however, responsibility on both sides of the border and both sides of the accession table. The European Parliament's latest assessment expresses regret at North Macedonia's lack of progress, calling for the constitutional amendments, stronger cross-party cooperation and deeper reforms. Yet that same resolution warns that bilateral disputes over language, culture and national identity should not be used to obstruct accession. This is the uncomfortable heart of the story: the EU must remain demanding enough for membership to retain meaning, while remaining fair enough for its promises to retain credibility. The rules were written for a different Europe Kojala argued that the enlargement machinery itself must adapt to a radically altered security landscape. The process still requires unanimity at critical stages, allowing one member state to hold up another country's progress. Under normal circumstances, such caution might be defensible. These, he stressed, are not normal circumstances. The EU's decision-making can be painfully slow because 27 governments must agree on decisions touching sovereignty, money and national interest. Kojala compared it to 27 friends attempting to choose a restaurant, except that several of them may not be friends and the decisions are monumental. The central question is therefore whether procedures devised 20 years ago are still adequate for a Europe facing war, cyber-attacks, sabotage, disinformation and growing competition from authoritarian powers. Railways, bridges and the architecture of security EU enlargement may sound abstract, but it rapidly becomes concrete. It is about railway lines, bridges, roads, energy systems and digital networks. Dimitrovski pointed to Corridors VIII and X, which cross North Macedonia and connect the Adriatic, Black and Aegean Seas with wider Europe. These routes matter for trade and daily life, but also for NATO's ability to move personnel and equipment across the continent. A bridge too weak to carry military vehicles is simultaneously an infrastructure problem, an economic weakness and a security vulnerability. Kojala offered a useful challenge to the language of cost. Security spending is often discussed as money disappearing from productive use. Yet roads, schools, housing, communications and transport capacity remain in the communities where they are built. The same is true of enlargement: investment in the Western Balkans is not charity at Europe's edge. It is investment in the resilience of the continent as a whole. A vacuum rarely stays empty Russia remains an influential force in Serbia and parts of Bosnia and Herzegovina, while Chinese lending and infrastructure investment have expanded across the region. Dimitrovski was careful not to suggest that the Western Balkans would simply abandon Europe for Moscow or Beijing. His warning was more subtle. Prolonged uncertainty can produce weaker institutions, frustrated populations and a region increasingly exposed to financial pressure, political manipulation and disinformation. Europe therefore faces a choice that is larger than whether another flag appears outside the institutions in Brussels. It must decide whether the Western Balkans are genuinely part of its future, and demonstrate that belief through fair conditions, credible timelines and visible results. Kojala described the European Union as something close to a “boring miracle”: cumbersome, imperfect and endlessly predicted to collapse, yet remarkably capable of adapting and surviving. That miracle now requires another act of political imagination. The Western Balkans have spent more than 20 years hearing that their future lies inside the European Union. Europe may now need to ask a harder question of itself: how long can a promise remain credible before waiting becomes its own form of rejection?

First, we speak with The Indian Express' Dheeraj Mishra about thefts that have been happening in the Indian Railways. He tells us that in the last few years 1.27 crore pieces of linen have been stolen by passengers from the bedroll kits provided to them in the Indian Railway AC coaches. He discusses the investigation, its findings, and the steps the railways are taking. Next, we speak with The Indian Express' Pratip Acharya about over 1800 trees collapsing in Mumbai, which led to three deaths and many people getting injured. He talks about the possible cause, what the BMC is saying, and the concerns such incidents raise regarding the management of the urban tree cover. (10:30)Lastly, we talk about a Jammu court allowing the Jammu and Kashmir Police to conduct a 10 day custodial questioning of three publishers arrested in connection with the publication of books allegedly glorifying separatists. (23:44)Hosted by Niharika NandaProduced by Shashank Bhargava, Ichha Sharma, and Niharika NandaEdited and mixed by Suresh Pawar

It's a corker tonight - the long-awaited network development episode for Yorkshire and the North East (outside of WY, SY and Tyne/Wear). Where are the gaps? What are the new bits of railway we need to maximise the railways' ability to get people and goods off the road?Join us for the first of a four-part mini-series!Support #Railnatter at https://patreon.com/garethdennis. Merch at https://merch.railnatter.uk. Join in the discussion at https://discord.railnatter.uk. You can also buy my book #HowTheRailwaysWillFixTheFuture: https://bit.ly/HowTheRailways

"I like it out here."Kazi - Jessica MorrisGloria - Siouxsie SuarezPhil - Edward Selvey IVFiona - Tess SegalVoon - Leeman KesslerEffie - Julie Cowden-StarbirdZebulon - Neal StarbirdCaspar - Joe FisherDavid - Quintin Jones Jr.Ree - Camille SmickerEx- Camille SmickerPeter - Joe FisherMystery Men - Joe FisherWritten by Joe FisherDirected by Joe Fisher and Finlay StevensonMusic:Life's Railway to Heaven - Smith's Sacred SingersUnderneath the Mulberry Tree - Pacific Coast PlayersOld Rose Waltz - The WesternersAll Tuareg music by Ebo KrdumSubscribe for early access, ad free episodes, additional content and more!Subscribe on Patreon: https://www.patreon.com/midnightburgerSubscribe on Apple Podcasts: https://podcasts.apple.com/us/podcast/midnight-burger/id1537653218How about some merch? https://www.midnightburgermerch.comRead and search Scripts with PodScripts: https://podscripts.app/Explore the Midnight Burger Wiki: https://wiki.weopenatsix.com/wiki/Main_PageFor more information on our show, visit our website: https://www.weopenatsix.comFind and support our sponsors at: fableandfolly.com/partnersSee Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

The national railway operator says China recorded more than 2.3 billion passenger trips in the first half of the year, up 5 percent. The railway network has facilitated increased travel for foreign passengers visiting under the country's visa-free policy.

Hello internet! On this week's episode we're going on another American Girl Doll reading adventure, this time to Glacier Park with KIT'S RAILWAY ADVENTURE! Enjoy and be sure to share with a friend!   Asian Pacific Environmental Network: https://apen4ej.org/our-work/ Help support this show and unlock bonus content! Become a member at https://maximumfun.org/joinshmanners

The US-Iran war has escalated significantly amid a second consecutive night of heavy American strikes on Iran and a furious response from Tehran.On today's episode of Iran: the Latest, Venetia Rainey and Sophia Yan look at why for the first time since the ceasefire in April, President Donald Trump ordered cruise missiles to attack a critical railway bridge used to trade with Russia and China.After Tehran responded with kamikaze drones and ballistic missiles targeting US military assets across Kuwait, Qatar, Bahrain, and Jordan, they ask what next for the peace talks. Plus, why the 2026 Nato summit's quiet winner is Turkey. Sophia dives into the country's exploding defence sector, its simmering rivalry with Israel, and how it has gone from black sheep to core member of Nato. And everything we know about the personalised handgun Erdogan gave world leaders as a farewell gift.HighlightsIran attacks more US bases across the Middle EastComes after Trump struck a key Russia-China railway link in IranCONTRIBUTORS:Venetia Rainey, co-host and executive producer @venetiaraineySophia Yan, co-host and senior foreign correspondent @sophia_yanWATCH US ON YOUTUBE: https://www.youtube.com/playlist?list=PLJnf_DDTfIVAif-vifC6F2aoPB8GIw6dkCONTENT REFERENCED:How Turkey is powering Europe's rearmamenthttps://www.telegraph.co.uk/world-news/2026/07/09/how-turkey-became-new-pillar-european-defence/Erdogan gives every Nato leader a gun as farewell gifthttps://www.telegraph.co.uk/world-news/2026/07/08/erdogan-nato-summit-fun-keir-starmer-donald-trump/Monday's episode: Where is Iran's new supreme leader?https://linktr.ee/iranthelatestProducer: Peter ShevlinVideo Producer: Max BowerResearcher and Social Producer: Anna HindmarshStudio Operator: Andy WatsonExecutive Producer: Venetia Rainey ► Sign up to our most popular newsletter, From the Editor. Look forward to receiving free-thinking comment and the day's biggest stories, every morning. telegraph.co.uk/fromtheeditor► EMAIL US: Contact the team on battlelines@telegraph.co.uk► GET THE LATEST HEADLINES: Find all our latest Iran coverage here: https://www.telegraph.co.uk/iran-war/ Hosted on Acast. See acast.com/privacy for more information.

How Modi's Investment in Railway Infra is making India Richer | Pakistan, Bangladesh Left Far Behind

Send us Fan MailThis week we had some excellent news..we've made the Longlist of the #BritishPodcastAwards 2026 in the factual category.. your time listening and suggestions for stories are really appreciated! Welcome to this episode where young reporter George Woodward and dad Tony catch up with Paul Middleton aka 'Piglet' the Director of Mechanical Engineering at North Yorkshire Moors Railway during filming for his new Channel 4 television series 'Steam Train Diaries'Sharon Gregory  takes a 'Railway Rideout' to Amerton Railway in Staffordshire and finds out about the 'Railway that never was' and Alasdair Stewart heads to one of London's hidden railway gems The Kempton Waterworks Railway to find out about its origins carrying coal to feed the triple expansion steam pumping engines that supplied water to London, through to the dedicated volunteers who are operating and developing it today!LISTENERS' CHOICE AWARDS #BRITISHPODCASTAWARDSWe are thrilled to be on the this year's Longlist of the British Podcast Awards 2026.If you would like to vote for us in the Listener's Choice Category you can do so  HERE . The first round is open until July 23rd 2026Links below to the Railways and Organisations we have mentioned:Steam Train Diaries Channel 4Paul Miller aka 'Piglet' - North York Moors Amerton Railway Hampton & Kempton Waterworks RailwayMWB No4 - Project websiteThis podcast is produced by Laura Raymond and presented by Alasdair Stewart and Sharon Gregory. Our 'Making Tracks' music is with kind permission of composer and musician Richard Durrant. It is a unique piece inspired by the rhythm of the historic rolling stock on the Ffestiniog Railway on the scenic journey from Harbour Station to Tan y Blwch. You can listen and download the full 'Tan y Bwlch' Ukulele Quartet here: Thank you to voice artist David King - for the Railway Ride outs voice over. Ukulele Quartet No. 1 "Tan y Bwlch"  Ukulele Quartet No. 1 "Tan y Bwlch" Richard Durrant · Single · 2019 · 3  songs.    

We've been running a bit of an Agent Cloud series surveying all the top inference/compute/cloud providers, from Databricks to Daytona to Railway and, even further back, E2B, but we're excited to conclude this series returning to Modal, which has just raised a monster $355M Series C.The cloud was built for developers. But agents are now changing that.The old infra stack was designed for a human who could read docs, reason through YAML, and understand dashboards to figure out what they need when something broke. While this was painful for developers, it worked since they could fill in missing context in their heads.However, agents don't have that luxury. Now in this new era of agents, everything has to be tighter.They need a place to write code, run it, inspect the output, change the environment, debug failures, and try again. Fast iteration and feedback loops with all the necessary context are crucial for agents to operate properly. Furthermore, sandboxes are a clear representation of this shift as agents can easily spin up isolated environments. This programmatic infra even extends to research:Two years ago, we were one of the first to cover Modal with CEO Erik Bernhardsson and Alessio designed our favorite LS thumbnail of all time:At the time, Modal was just a teeny little company with a $17M Series A.Today, fresh off their $355M Series C, Modal is one of the clearest examples of the agent cloud future being built in real time: a cloud platform moving past traditional web app assumptions toward the workloads AI actually creates such as elastic inference, sandboxes, GPU burst, post-training, background agents, and infrastructure that agents themselves can operate.In this episode, Modal CTO Akshat Bubna joins swyx and Vibhu to unpack why AI applications don't fit traditional cloud assumptions, why Kubernetes was never designed for bursty compute-heavy workloads, and why Modal is now shifting from developer experience to agent experience.We go deep on Modal's AI infra stack: serverless functions, decorator-based infrastructure, elastic inference for custom models, GPU snapshotting, DeFlash, speculative decoding, Auto Endpoints, sandboxes, persistent storage, networked containers, private IPv6, RDMA, multi-node training, and Modal's capacity pool across 17 cloud providers. Akshat also explains why RL rollouts can require 100,000 sandboxes, why production agents need hard guardrails, why observability may matter more than reading code, and why AI has made infrastructure exciting again.We discuss:* Why Kubernetes wasn't built for bursty AI workloads* How Modal started as a better runtime before becoming an AI cloud* Why Modal added GPUs before ChatGPT* The shift from developer experience to agent experience* Why observability matters when agents are writing the code* Elastic inference for custom models across audio, video, robotics, and comp bio* GPU snapshotting, cold starts, and why inference workloads are so bursty* Why RL rollouts can require 100,000 sandboxes* DeFlash, speculative decoding, and frontier-level inference performance* Auto Endpoints and making optimized inference easier to deploy* What Modal adds beyond vLLM, SGLang, and raw GPU rental* Modal's 17-cloud capacity pool and supercloud strategy* Networked sandboxes, sidecars, private IPv6, and RDMA* Serverless multi-node training for post-training and research workloads* Auto-research, model-guided sweeps, and agents launching GPU experiments* Compute strategy, capacity planning, and batch tiers* Why production agents need specialized sandboxes and hard guardrails* Modal's take on managed agents, CI, Gitpod/Ona, Python, TypeScript, and Modal BenchAkshat Bubna* LinkedIn: https://www.linkedin.com/in/akshat-bubna-188885103* X: https://x.com/akshat_bModal* Website: https://modal.comTimestamps00:00:00 Introduction00:00:39 Modal's origin and why Kubernetes wasn't enough00:04:32 Developer Experience → Agent Experience00:06:21 Modal's AI cloud primitives00:09:14 Sandboxes, agent loops, and proto-Cognition00:12:12 Elastic inference, GPU snapshotting, and 100,000 sandboxes00:15:24 DeFlash, speculative decoding, and Auto Endpoints00:19:59 Production-grade inference beyond raw GPUs00:22:00 Background agents, Ramp Inspect, and the agent lifecycle00:24:08 Modal's 17-cloud supercloud strategy00:26:40 Networked sandboxes, private IPv6, and RDMA00:32:48 Multi-node training, post-training, and auto research00:37:36 Compute strategy, capacity planning, and batch tiers00:40:55 Open models, real-time AI, and production agent infra00:43:06 Hard guardrails, managed agents, and specialized sandboxes00:46:06 Why AI made infrastructure exciting again00:48:30 Model APIs, differentiated products, and agentic video00:51:50 CI, coding-agent infra, SDKs, and Modal Bench00:57:28 Closing ThoughtsTranscriptIntroduction: Modal, Series C, and the Art PartySwyx [00:00:00]: We're here with Akshat, CTO of Modal, together with Vibhu. Congrats on your Series C.Akshat [00:00:10]: Thank you.Swyx [00:00:11]: Your party yesterday was amazing.Akshat [00:00:15]: Yeah.Swyx [00:00:15]: From all the photos and all the swag.Akshat [00:00:17]: We had a bunch of art installations, which was fun, seeing, like, our products on pedestals next to, like, Rodin.Swyx [00:00:25]: Very nice. Very nice. When you started, it was not the GPU inference company. Maybe it was in your mind. Take us back to the origin story.Modal's Origin: A New Runtime Beyond KubernetesAkshat [00:00:39]: I first met Eric, who's the CEO, through an investor. Back then Eric was already thinking about building, a new runtime, and he got there thinking through why are workflow orchestration products so hard to use. It's because you have to run them on Kubernetes. Kubernetes is hard to manage. It's not built for burstiness and, custom images,Swyx [00:01:03]: YeahAkshat [00:01:03]: It has a terrible developer experience.Swyx [00:01:05]: And I'll, I'll interjectAkshat [00:01:06]: YeahSwyx [00:01:07]: For listeners, who are new, we interviewed Eric two years ago, and there's a bit more of the story there from Spotify and all those things.Swyx [00:01:14]: And I came across Eric through Data Council because he did that talk on the serverless container stack that you guys did, which was like, that was my first like, “Okay, I need to take Modal very seriously” moment.Akshat [00:01:26]: Yeah.Swyx [00:01:26]: But it was still very unclear, like, do I need all this for just my data pipelines?Akshat [00:01:33]: Yeah. initially what we were thinking about was if we build a better runtime, it's a very useful primitive in itself. It's There's a lot of things that, get solved by serverless functions, like you can do, ETL stuff, you can do job queues, you can do all this, like, bursty processing, which it turns out every company had needs for. but then we also were thinking about this as like, this is a primitive that we can build a whole collection of products on, which are very verticalized. So perhaps data engineering would've been the first one, but we were thinking about inference. Back then it was more classical inference, like computer vision stuff and running XGBoosts and whatnot. But we added GPUs to the product a year before ChatGPT came out.From Serverless Containers to GPU WorkloadsSwyx [00:02:19]: Nice.Akshat [00:02:19]: We just didn't think it would be that big of a deal.Swyx [00:02:22]: Yeah, just like add A100.Vibhu [00:02:23]: Was there any, like, early key problem that really sparked off why you built it?Akshat [00:02:28]: Yeah. Primarily it's just, none of the tooling that was out there was built for, one, a really great developer experience, and also there's a general trend of, a lot of the workloads that we were seeing were very. I wish there was a better word for it, but compute-heavy. Like, they need, one, like, need a lot more resources, so you need to burst up and down a lot, versus like Kubernetes designed for, like, slow scaling and, more for, like, web server use cases. And also there's just a lot more specialization in, like, what kinds of environments these workloads run in. Like, we had sometimes they need accelerators, sometimes they need different kinds of images, and this is just like a consistent thing that we saw across a lot of companies. That would be the next step.Software-Defined Infrastructure and Decorator-Based DXSwyx [00:03:13]: Yeah. Yeah. Be nice. I don't know how much this factored into the early story, but I wrote a post when I was at Temporal about infrastructure, software-defined infrastructure or something like that.Akshat [00:03:22]: Yeah, the self-provisioningSwyx [00:03:23]: Self-provisioning.Akshat [00:03:24]: Yeah.Swyx [00:03:24]: Yeah. I can't even remember my own post.Swyx [00:03:26]: And then you put me on the landing page.Akshat [00:03:28]: Yeah. We really like, the term and so we stole it.Swyx [00:03:32]: Because you had the insight that everything can just be in decorators co-located with the code, right?Akshat [00:03:37]: Yeah.Swyx [00:03:37]: Was that a big part of the originalAkshat [00:03:39]: YesSwyx [00:03:39]: Story or it was just like a DX layer?Akshat [00:03:41]: That was, really important because we really didn't want people to spend, so much time, writing YAML, and it seemed like you could really condense the surface area of what you're doing, put it in code so you can operate on it just like you operate on other code, and like build stuff that's more expressive and dynamic. and so yeah, that was always a very important part.Swyx [00:04:04]: Then the pushback is this is a DSL.Akshat [00:04:07]: Yeah.Swyx [00:04:07]: It's you're closed source. I am locked into Modal.Akshat [00:04:11]: Yeah. We never really got pushback for that because the nice thing about Modal is you can bring whatever code you have, and sure, the DSL is at the configuration layer for, what hardware you're using, how you're scaling things up, but you still own the code.Akshat [00:04:27]: And that's, that's been an important, part of our story, even as we do inference now.Swyx [00:04:32]: Yeah.Vibhu [00:04:32]: How much of do you think still stays the same today? Like if you were to build something today, DevX very important, but I feel like, a lot of this has been changed with just hook it up to an agent, have Claude Code, have Codex implement a tool. there's very agent native primitives that are different than if I'm doing this myself, right?Developer Experience → Agent ExperienceAkshat [00:04:54]: We've changed our SDK team to think about agent experience instead of, developer experience and we think that the same benefits that apply for DX also apply for AX, which is why would you have an agent read through hundreds of Kubernetes files and like write YAML that's not even typed when it can make a couple of changes in a decorator and it gets this self-provisioning runtime of, being able to see its changes live in action? yeah, it just seems from the customers we talk to, they find Modal is much faster for agents to use versus operating on a different substrate.Swyx [00:05:34]: Yeah, because like you, again, you co-locate the infrastructure requirements to the code that runs it.Akshat [00:05:38]: Yeah.Swyx [00:05:38]: Well, the negative thesis now is that nobody's looking at their code anymore, so there's no point.Akshat [00:05:44]: Yeah, people aren't looking at code. one thing we still see is really important is observability.Swyx [00:05:51]: Yeah.Akshat [00:05:51]: Like how good is your dashboard? And of course, like we have, we push a lot of it to the CLI so the agents can do their own investigation, but you still need humans to go interpret what's going on and, make judgment calls and whatnot. and that's I feel like, Maybe more important now than looking at the code itself.Swyx [00:06:11]: Yes, because like, you can try to treat the code as a black box and then use, see the observable action that comes out of it, and then just prompt a change.What Modal Is For: AI Cloud PrimitivesAkshat [00:06:21]: Yeah.Swyx [00:06:22]: So I think it takes a bit of restraint to not specialize, to say, “I want to ship a new primitive,” and then just be general purpose.Swyx [00:06:31]: People ask you, “What are you for?” You're like, “ I don't know. We can do this, we can do that.”Vibhu [00:06:36]: Well, I'd be curious to see, like, okay, if we were to ask you, like, what is Modal for even at a high level? There's a lot you guys do, sandboxes, GPUs, everything. How do you answer?Akshat [00:06:46]: Modal is a cloud platform that's built for, where we've built the primitives from scratch for AI applications. and right now it covers, inference, training, batch processing, and sandbox workloads.Akshat [00:07:00]: But we're building a lot moreSwyx [00:07:02]: I noticed you didn't say web server, so there is still a role for, like, the always-on large-scale Kubernetes type things.Akshat [00:07:09]: Yeah, absolutely. We're, we're not trying to compete with the renders of the world, because yeah, we think the differentiator for us is the, are the workloads that need specialized compute, need to scale up and down a lot. yeah, they're, they're, they're just shaped differently.Working Alongside Frontier StartupsVibhu [00:07:26]: I think you're building a lot of it alongside the startups, right? They're innovating quite a bit, even in your, like, latest blog post. Like, even in the series C, the customers that you mention here, the cognitions, technical ones, ramps and whatnot, they're, they're innovating with you, right? And that's not something AWS is doing directly with.Akshat [00:07:45]: Yeah, absolutely. I think, this is again classic. We're a small team. We can move really fast. our engineers are working with our customers and figuring it out. Yeah.Swyx [00:07:54]: So my first week at Cognition, I walked in, there was someone wearing a Modal shirt. I was like, “What are you doing here?” They're like, “Yeah, I just. I am embedded inside of Cog.”Akshat [00:08:05]: Yeah, I think that was Peyton. We sent him overSwyx [00:08:07]: Yeah.Akshat [00:08:07]: Because, the latency of communication was too high otherwise.Swyx [00:08:12]: Yeah, distributed node, you have to - you have to place one and collocate.Vibhu [00:08:16]: Yeah.Swyx [00:08:16]: So I had a, I had direct personal experience, right? So I worked on smol developer three years ago. it was inspired by Claude 1. I think you onboarded me at some point, like, just before, and I was like, “Oh, like, I need some bursty compute. Like, I was just gonna try using Modal.” And it was a, it was a pretty pleasant experience. apparently, I showed up in the board meeting, like the analytics.smol developer, Sandboxes, and Proto-CognitionAkshat [00:08:39]: Yeah, you blew up on Hacker News and,Swyx [00:08:41]: YeahAkshat [00:08:41]: We got a big traffic spike. I. I think the way you used smol developer was Modal functions for running stuff, which was. Like, the, that was a good use case. but then, yeah.Swyx [00:08:53]: Yeah. That - So to me, that was proto-cognition.Akshat [00:08:55]: Right.Swyx [00:08:56]: If only I had, like, stuck to it.Swyx [00:08:58]: Like, that was like, if - did you say draw the tech treeAkshat [00:09:00]: AbsolutelySwyx [00:09:00]: You're just like, “Yeah, like, probably this will happen.”Akshat [00:09:02]: Yeah. Like, he was so close. You were just rebuilding upon usSwyx [00:09:04]: I just didn't realize.Akshat [00:09:05]: But the funny story there is at the same time, we were talking to a bunch of customers who needed something like sandboxing.Swyx [00:09:14]: Yeah.Akshat [00:09:14]: This is like twenty-three.Swyx [00:09:15]: Yeah.Akshat [00:09:16]: So we builtSwyx [00:09:17]: You introduced a new API right after that.Akshat [00:09:18]: Yeah.Swyx [00:09:19]: Yes.Akshat [00:09:19]: Like, we built sandboxes in May of twenty-three before anyone was even knew this was gonna be a thing. And the first example we published was, we took smol developerSwyx [00:09:28]: Smol developerAkshat [00:09:28]: And put it in a loop, so the agent can iterate on itself.Swyx [00:09:33]: Loops are hot these days.Vibhu [00:09:34]: It's the looper.Akshat [00:09:34]: Yeah.Vibhu [00:09:35]: Loops in. When was this, twenty-three?Akshat [00:09:38]: Yeah.Vibhu [00:09:39]: A small check.Akshat [00:09:39]: Yeah.Swyx [00:09:39]: It's like twenty-three. so the. the, those for listeners, like, the problem was the models are not built for any of this, right?Swyx [00:09:46]: Like, you're just trying to like. They're not post-training to understand, like, looping and, like, self-correction and tool calling was there, but, like, also not that great.Akshat [00:09:55]: Yeah.Akshat [00:09:55]: I don't remember if you used tool calling in this one, but yeah, the models would just diverge after like ten iterations and not produce anything meaningful.Swyx [00:10:03]: Yeah. But like, then. So okay, like now talking to myself three years ago, the answerVibhu [00:10:08]: Of course they will get betterSwyx [00:10:09]: Collect all the failures, build benchmark, and then collect all the, examples, build the RL environmentAkshat [00:10:15]: RightSwyx [00:10:15]: Sell it for like ten billion dollars to Meta.Swyx [00:10:17]: And then also train a model and then sell that for sixty billion dollars to Elon. And this isAkshat [00:10:23]: Yeah, of courseSwyx [00:10:23]: The funny machine. Like, it's like, it's about the hardware.Akshat [00:10:28]: It's hard to have that inherent conviction that the stuff will get that much better.Swyx [00:10:33]: In retrospect, it's so f*****g obvious.Akshat [00:10:36]: Fair enough.Swyx [00:10:37]: Like, what else were we doing back then? I don't know. anyway. Yeah. So this. That was the start of your sandboxing journey, right? I feel like it didn't blow up until, like, last year.Akshat [00:10:49]: Yeah.Swyx [00:10:50]: So there was like a couple years of quietness.Akshat [00:10:52]: Exactly, yeah. We wereVibhu [00:10:53]: I think very underrated product value. Like, my experience with Modal, Charles, before he had joined Modal, met this guy at a hackathon, and he really insisted we wanted to run some small model, not hosted anywhere, and he's like, “ there's this cool company, Modal. They'll like spin up a GPU sandbox, we can throw it on there. They'll take a Hugging Face link.” And like there's so much value just right there, right? Like instant hosting, spin it up, spin it down. It'll stay cold, but we run the demo a few days later, it'll come back up and like all this stuff in retrospect, like it's still what we needed like today.Akshat [00:11:27]: Yeah, it's still needed today. workload shapes have changed a lot as, we run stuff for people with really massive production scale and, there it's it's not about scaling from zero to one, but it's how do we scale really elastically, from like thousand to fifteen hundred GPUs very quickly in a given region. It's the same shape problem.Elastic Inference, GPU Autoscaling, and Custom ModelsVibhu [00:11:50]: Okay. So you look at, say, Cursor Composer, right?Akshat [00:11:53]: Yeah.Vibhu [00:11:53]: They had a. “We'll do RL on a model every couple hours.” you guys have a whole version of RL inference gym and whatnot.Vibhu [00:12:01]: When you look at workloads like that, you're doing train runs where you need to scale up, scale down every hour thousands of GPUs, right? That's the example for we do need it, right?Akshat [00:12:12]: Yeah. Well, so I'll, I'll take a step back and, maybe talk about like how people use Modal today. because our biggest use case is, elastic inference. And the thing we first found product market fit, with was inference for custom models. So we stayed away from the LLM space, and we were serving companies like Suno for audio, Runway for video, robotics, comp bio companies that train their own model elsewhere. But Modal is the best black box that for deployment, scaling to however many GPUs you need as your traffic pattern changes. And we saw all of them like have a very unpredict- predict- predictable, traffic pattern. it's like diurnal. It's Some days, like the company will do a launch and, they'll need like, way more. And it's not just one model that they deploy. They-- all these companies deploy, lots of different models in different regions, and so the autoscaling problem becomes even harder because then you have to scale within a certain region, and those cycles are offset. So different times you scale up in different regions.Akshat [00:13:20]: So that's like our sortVibhu [00:13:22]: And thatAkshat [00:13:22]: YeahVibhu [00:13:22]: That in and of itself is a huge category. There's a bunch of inference providers which, provide this fireworks, does this as a service together, whatnot, Base10. that's carved into its own niche for language models, at least right now.Akshat [00:13:36]: Yeah. the thing that we have specialized in is the autoscaling aspect.Vibhu [00:13:41]: Yeah.Akshat [00:13:41]: Because we found that it's not universally true that everyone else can autoscale, and we've gone deeper into it on the tech side by, we've incorporated GPU snapshotting into the product so we can take the GPU state, like your torch.compile model, snapshot it, and the next cold start is way faster. And so going back to your question, it's That's why you need a lot of burstiness for inference. But then people also do a lot of demand training, like for RL stuff, your rollouts are bursty, as you said. People also do a lot of batch jobs. So we'll see, a lot of companies, before they have a training run, they'll need thousands of GPUs to run encoding or something like that. And I think those things are much more bursty than. I agree that agents are not that bursty. sandboxes are, except when you're doing RL. RL is justRL, Batch Jobs, and 100,000 SandboxesVibhu [00:14:28]: Or commerceAkshat [00:14:28]: Insanely bursty.Vibhu [00:14:29]: Yeah.Akshat [00:14:30]: Yeah. Like when you're doing, rollouts, you sometimes need a hundred thousand sandboxes in your sandboxes.Vibhu [00:14:37]: Yeah. I'm curious if you've seen early sparks of continual learning. There are some people, like our friends, ngram, recently announced thisAkshat [00:14:45]: YeahVibhu [00:14:45]: They're, they're trying to do training. That also seems like a different workload, right? If you're doing training twenty-four/seven per se, there's a very weird dynamic of how you're using GPUs between people and whatnot, but seems like something you guys would work for.Akshat [00:15:00]: As you said, we're, we're fortunate to work with a number of, customers at the frontier and grab some of our customers. and they are taking the primitives we have, and trying to use them in very interesting ways, like continual learning. It's possible as the stuff gets better, some of that will be part of, our offering as well if, more people need it. but we're, we're just waiting to seeVibhu [00:15:23]: YeahAkshat [00:15:23]: How it shakes out.Vibhu [00:15:24]: Is there a primitive that you added after sandboxing that was the next step in the story?LLM Inference, DeFlash, and Speculative DecodingAkshat [00:15:32]: I guess we've been going much deeper into LLM inferenceVibhu [00:15:35]: YeahAkshat [00:15:35]: Because we realized that some of the advantages we have with like autoscaling, again, especially in different regions and whatnot, are, not present elsewhere. and the place where we had a gap was we weren't, working on the model layer itself. Like we were a black box. And, we realized that, we can get to frontier-level model performance, with, by having great people who work on this. And, we've been open sourcing a lot of our work, in terms of, Recently, we, shared our work on DeFlash, which is a block-based, speculator, and we've open sourced, all of it. So, you can - By using open source DeFlash, you can get the same performance as you would with one of the proprietary providers. And the next thing we're thinking about hereVibhu [00:16:23]: I thought this wasAkshat [00:16:24]: YeahVibhu [00:16:24]: An interesting blog post as well, right? Like, I think in here you make a claim that. Not a claim, just that how effective speculative deco-decoding really just get to.Akshat [00:16:33]: Yeah.Vibhu [00:16:33]: Anything you wanna point out from this around, what people should know?Akshat [00:16:39]: Yeah, absolutely. the high-level summary is, it would help to describe what speculative decoding is.Vibhu [00:16:44]: Yes.Akshat [00:16:44]: I will, yes.Vibhu [00:16:45]: I think, likeAkshat [00:16:46]: YeahVibhu [00:16:46]: So we've covered like Eagle and all thisAkshat [00:16:47]: YeahVibhu [00:16:47]: Like Hydra and all those things, but it was like two years ago.Akshat [00:16:51]: Yeah.Vibhu [00:16:51]: I think it doesn't hurt, right?Akshat [00:16:52]: Yeah. Speculative decoding is you have a smaller model, called a draft model, predict tokens ahead of the bigger model, and then you have the bigger model, verify all of this, all the tokens are predicted. And the reason it's faster is if you're predicting, one token at once, you're bound by memory bandwidth. But if you can batch the verification of, the draft model, then you're much more efficient using compute, and it's faster, and as long as your draft model is producing a lot of tokens that can get accepted, which is called the accept length, you can get a speed up that's, multiple times of, the original model speed. and well, that's what we highlight here. It's Like people talk a lot about we made these kernels faster and whatnot, but improving kernel will only give you like few percentage points of improvement, and, increasing accept length, literally is a multiplicative decreaseVibhu [00:17:47]: Like two to four X.Akshat [00:17:48]: Yeah, exactly.Vibhu [00:17:48]: Without much head-on performance.Akshat [00:17:50]: Yeah. I think it may - you are running a second model, right? So it may be something more expensive in the compute,Vibhu [00:17:57]: I meant quality performanceAkshat [00:17:58]: Probably not by muchVibhu [00:17:58]: But yeah. I thinkAkshat [00:17:59]: So there's no drop in quality performanceVibhu [00:18:01]: YeahAkshat [00:18:01]: Because you're always. You're never accepting a token that the big modelVibhu [00:18:04]: It's strictly betterAkshat [00:18:05]: YeahVibhu [00:18:05]: Or it's same.Akshat [00:18:06]: Exactly.Vibhu [00:18:07]: Right. Yeah.Akshat [00:18:08]: And so we've been working a bunch on DeFlash, which is a block-based speculator. so it's instead of predicting, one token at a time, it's predicting a block. And we've been open sourcing our work with it. The next thing for us here is for helping people train speculators and custom models. it's it's something that traditionally is very forward-deployed engineering driven, support deployed, engineer driven, like you work with customers and help them do that. And our vision for. This is why we launched Auto Endpoints, is we want to make frontier-level performance available to everyone. And so, we mentioned this in the announcement, we teased it. The next thing we're, we're launching is, as you run an auto endpoint, we shadow trafficAuto Endpoints and Frontier-Level PerformanceVibhu [00:18:54]: Do you want to explain what auto endpoints are?Akshat [00:18:57]: Yeah.Vibhu [00:18:57]: I lovely, yeah.Akshat [00:18:58]: Yeah. So, this is, I guess, going back to your Modal is you touch the code, but, sometimes people don't wanna touch the code, and they wanna get started with an endpoint that works and has all the great performance and, scalability that Modal has. So we've made that easier with, a way to create an endpoint from our UI, from the CLI, that has all of our optimizations that we talked about, like the DeFlash stuff already baked in, and there's full transparency. So we give you the code, you can go run it yourself, and if you want, you can eject out into the full Modal experience, which we see as people get sophisticated, they do wanna tweak the models, they wanna, fine-tune stuff. You can still do all of that. It's it's not a black box. And yeah, the next thing, as we teased later in the post, is how do we give you value even beyond this in terms of having your draft models evolve as your data distribution evolves, again, without having to talk to a person and, yeah.Vibhu [00:19:59]: I guess just to understand it directly, you have the GPUs, you have an endpoint that's compatible, you serve open model. If someone was to do this themselves, what's the delta that you guys provide? So you do a lot of open source great work on effective inference. how does it compare to, say, I take the same model, 5.2 FP8, take shelf inference engine, vLLM, SGLang, get compute of similar capacity, similar cost. What's the delta that plugging into something this, like this offers outside of the benefit of, scaling?Production Inference Beyond Raw GPUsAkshat [00:20:34]: It's interesting because we've taken the approach of open sourcing our contributions and upstreaming them. we work closely with the SGLang team. We want the improvements that our team, comes up with to be, there in open source for others to use, even outside of Modal. The benefit to us is we have a team that has significant expertise in terms of if you do have something that is not there, our team can help you get that performance, first. the other thing is with these endpoints, we are way more elastic, as you said, than, anyone else, and you have true scaling to zero. you have true, burstiness, and in practice, that matters a lot more to people than just finding, the GPU and, running Modal code on something.Vibhu [00:21:20]: Yeah. And I will say it's not that straightforward to just. like what I said is easier said than done, right?Akshat [00:21:26]: Yeah.Vibhu [00:21:27]: It's I think still for the average person, still hard to just gut check using different. There's, there's quite a bit of combinations you can make there. the trade-offs aren't really known at face value.Akshat [00:21:40]: Yeah. it's it's not just that. I think it's it's that running production-grade inference is a hard infer problem.Vibhu [00:21:49]: YeahAkshat [00:21:49]: Even if you subtract out the autoscalingVibhu [00:21:50]: YeahAkshat [00:21:51]: Is controlling things like tail latency and, making sure every, request is delivered at least once and whatnot.The Model and Agent LifecycleVibhu [00:22:00]: There's a lot of innovation that you can do here. I think, it's very interesting that you're starting to encroach on, like as you become a full cloud, you're starting to encroach on other people's turf.Vibhu [00:22:09]: What will you not do?Akshat [00:22:13]: Well, we wanna follow our users and, make sure they get like a platform that has everything that works well together. so right now we're focused on the model lifecycle and the agent, lifecycle. so both like going from data prep to training to inference, and then also if I want to deploy a background agent, let's say, sandbox, do persistent storage, a whole bunch of other stuff.Vibhu [00:22:38]: We talked to Cole, who did, OpenInspect. Yeah.Akshat [00:22:42]: Yeah.Vibhu [00:22:42]: And RealInspect also is on Modal.Akshat [00:22:44]: Yeah. So Ramp Inspect was a great example of a background agent that was really successful because they, were able to use some of the primitives like snapshotting and fast scaling to just have something that feels really reactive and works well.Ramp Inspect and Background AgentsVibhu [00:23:02]: Yeah. That's the new CTO of, Ramp right there.Akshat [00:23:05]: Yeah, Rahul.Vibhu [00:23:08]: It was really fun. yeah, okay, I think, all very bullish. Like, one of my reflections was also I did not originally. So when I met you guysThe Inference Inflection: CPU, GPU, and Co-LocationVibhu [00:23:19]: You weren't that much in the GPU game, and now you're all about, inference. And one of the points that I hinged on for Jensen's keynote at GTC this year was, what we're calling like the inference inflection, right? That let's say in AI workloads or machine learning workloads, it used to be like, let's call it eight to one GPU to CPU, and now it's more like one to one, which is like a interesting. Like, - because of how much agents are blocked or call out to this, to CPU heavy stuff the actual, like, limiting factor, like, swings back and forth from GPU to CPU a lot more than it used to be all GPU and then occasional CPU.Akshat [00:24:01]: Yeah.Vibhu [00:24:02]: GPU, CPU. And now it's like just constantly, and you just have to locate everything.Seventeen Clouds and the Supercloud StrategyAkshat [00:24:08]: Yeah. And that's one of the things that, again, we see as, something appealing about Modal, which is we've built this capacity pool that spans, 17 cloud providers, so we're, we're very good at Running on various kinds of cloud capacity across the worldSwyx [00:24:24]: You don't have your own data centers?Akshat [00:24:25]: We don't have our own data centers. We just run across a lot of neo cloudsSwyx [00:24:29]: Yeah. AreAkshat [00:24:30]: Metal providers.Swyx [00:24:30]: Yeah. Question mark.Swyx [00:24:31]: Yeah. You're, you're running the math, and you're like, “What's the cutover point where you're like.”Akshat [00:24:36]: Yeah, it's a good question. part of it is we see our differentiator in the software layer, and, being capital light and focusing on the software helps us move really fast. so far it's worked out well because there are so many other people building data centers that we're able to work effectively with them, and again, focus on what makes us, special.Swyx [00:24:55]: Yeah.Swyx [00:24:56]: 17 gets you into, like, the local providers sometimes. LikeAkshat [00:25:00]: The,Swyx [00:25:01]: Which was the most interesting one?Akshat [00:25:02]: There are a lot more neo clouds than you expect, and they all have various degrees of, various levels of reliability. And, that's why it's something we've invested a lot of time in, is building our own reliability layer on top. so if the GPU falls off the bus or something happens, we user workloads are not affected, and that lets us use a lot more capacity than,Swyx [00:25:30]: YeahAkshat [00:25:30]: You as a user would be able to.Swyx [00:25:32]: It's a useful thing to have because like now everyone knows, like, what layer you are and, like, you optimize for being the super cloud of all clouds.Akshat [00:25:41]: Yeah. That's, that's, that's the idea. and so I guess when you mentioned colocation, that's, that's another interesting thing where, one thing we've seen is people come to us when they want, very specifically located, CPUs or GPUs, like they wantSwyx [00:25:57]: Oh, they pin it in likeAkshat [00:25:58]: YeahSwyx [00:25:58]: EU?Akshat [00:25:59]: Exactly. Or EU, US.Swyx [00:26:01]: Right. Data resiliencyAkshat [00:26:02]: AustraliaSwyx [00:26:02]: Locality thing or performance or what?Akshat [00:26:04]: It's either data locality or latency, yeah.Swyx [00:26:07]: Yeah.Akshat [00:26:07]: Like, you want your. They're running sandboxes and model. They want them to be right next to aSwyx [00:26:10]: Yeah, it's easy thenAkshat [00:26:11]: YeahSwyx [00:26:12]: To. That is important in all those things. and so, like, you've accidentally, I don't know if it's accident, but, like, you've built the perfect primitive for agents to express themselves. And then, like, it's almost very funny how every extra development just involves more file system, just involves more CPU.Akshat [00:26:30]: Yeah.Swyx [00:26:31]: Just like the things that you already have. I don't know much about, if there's any, like, networking usages that are interesting, but you've also done some good work on networking.Networking, Sidecars, Private IPv6, and SandboxesAkshat [00:26:40]: Yeah, that's exactly right. Like, we're just taking compute storage and networking and building stuff on that layer, for, again, the stuff people need.Swyx [00:26:49]: YeahAkshat [00:26:50]: We see a few interesting networking things coming up. one is people want networked sandboxes. so we haveSwyx [00:26:57]: For like a Docker cluster type thing.Akshat [00:26:59]: Yeah.Swyx [00:26:59]: Sorry, Docker Swarm. Oh, f**k. What is it called?Akshat [00:27:02]: Compose.Swyx [00:27:03]: Compose type thing.Akshat [00:27:04]: Yeah. So if you want Docker Compose, our sandboxes now support, this thing called sidecars. So you can. A sandbox is a pod of containers, and you can run multiple containers in, a sandbox. also useful because, going back to networking, people want a lot of control over, outbound networking from a sandbox.Swyx [00:27:23]: Yeah.Akshat [00:27:23]: Like, they might wanna run a middle proxy for, like, maybe logging stuff for RL or, controlling how egress can happen to a domain, injecting credentials. and yeah. So we've, we've had to build a lot of that stuff ourselves.Swyx [00:27:38]: Yeah.Akshat [00:27:39]: But then also sometimes people want, sandboxes spanning multiple nodes to talk to each other, which is an emerging thing we're seeing. We have support for that for a different reason, and yeah, we'll see if that becomes stable.Swyx [00:27:52]: Like, just an open socket. It's a. This is directly like mTLS.Akshat [00:27:56]: We do support that, which is you can, expose a tunnel inside a sandbox.Swyx [00:28:01]: Yeah.Akshat [00:28:01]: And then you can either expose it to public internet or it can be, you can add like a HTTP, auth layer above it. But we have this thing called I6PN, which we haven't talked about, which is this, like, overlay network using IPv6 addresses. so if Modal containers, within the same workspace, when this is enabled, can address each other using this private IPv6 address, and no one else can.Akshat [00:28:28]: So it's like private networking, for containers. We built it because we needed it as a primitive for our distributed training product. so we have this other feature, which is you can add a decorator to a function, and you get a cluster of GPUs. and they have RDMA networking. so you can run a distributed training job, that's truly serverless. and we did the overlay network for that. But then we've seen that people are using it for other reasons, and, I'm intrigued to yeah, what would people do with it.Swyx [00:28:59]: Build primitives and let people figure it out, right?Akshat [00:29:01]: Yeah, exactly.Swyx [00:29:02]: You put out a pretty interestingAkshat [00:29:03]: They're like, they read the docs webpage. Let me use thatSwyx [00:29:06]: YeahAkshat [00:29:06]: Something they never intended to work. This is literally not even in our docs page. People somehow found it, and they're using it.RDMA, Memory Movement, and Distributed TrainingSwyx [00:29:12]: Huh.Swyx [00:29:14]: The way you portrayed it with, like, RDMA versus TCP, like, very well laid out, but just the transfer speed change at scale for RL, like yeah, you have it, you have it built in. I'm sure someone found it. It's found it to be a lot more efficient before you made a thing out of it, right?Akshat [00:29:32]: Yeah. And not to split hairs, I guess the overlay network is the TCP overlay network.Akshat [00:29:39]: The reason we have that is you need that to do the key exchange for RDMA before you set up the RDMA network on top of that. but then people found the TCP part.Swyx [00:29:48]: Can I tell you, this is like a big aha moment for me becauseAkshat [00:29:51]: YeahSwyx [00:29:51]: So I review 2,200 submissions for the World's Fair.Akshat [00:29:56]: Yeah.Swyx [00:29:57]: And then I got this from John OsterhoutAkshat [00:29:58]: HuhSwyx [00:29:59]: Who I don't know if. Do John Osterhout by name?Akshat [00:30:01]: The name sounds familiar.Swyx [00:30:02]: He published a. He's a well-known professor, published a lot of interesting software design books, and this is the talk he chose to submit, is on RDMA at Inference. And I'm like, you wouldn't think that this guy, who is like operating systems guy, would care about RDMA.Akshat [00:30:20]: I, it makes sense to me because I,Swyx [00:30:24]: This is the cloud, right? YeahAkshat [00:30:25]: Like, the way you move around your KV cache and how efficiently you can do it, how efficiently you move, your weights from your training GPUs to your inference GPUs in RL is there's a lot of degrees of freedom, and it is a systems problemSwyx [00:30:41]: YeahAkshat [00:30:41]: Moving memory aroundSwyx [00:30:42]: YeahAkshat [00:30:43]: Scheduling.Swyx [00:30:44]: This shows you how primitive my understanding of networking stuff is.Swyx [00:30:46]: Is this like the domain of WireGuard as well?Akshat [00:30:50]: Not quite.Swyx [00:30:51]: It's adjacent?Swyx [00:30:53]: Explain everything.Akshat [00:30:54]: Sure.Swyx [00:30:56]: How do we move memory around GPUs?Akshat [00:30:58]: Well, so sorry. Yeah, that is memory. Sorry, I was talking more, and maybe I was talking like five minutes back, about the private IPv6, addressing that you've set up.Swyx [00:31:09]: Yeah.Akshat [00:31:09]: Is it like it's a VPN?Swyx [00:31:10]: Yeah, it is like a VPN, and yeah, WireGuard is, yeah, you're right. It is,Akshat [00:31:16]: Right. Yeah, you already moved on to new topicsSwyx [00:31:17]: A similarAkshat [00:31:18]: OkaySwyx [00:31:19]: In the same space, WireGuard is, encrypted and this is,Akshat [00:31:23]: And you don't need encryption.Swyx [00:31:23]: Yeah.Akshat [00:31:24]: Yeah.Swyx [00:31:24]: This is not encrypted. that's the main difference. This is TCP and we have eBPF programs that will reject or allow the TCP connection based on whether you're allowed to do it.Akshat [00:31:35]: Used to involve a full sidecar, but now you have eBPF in the Linux kernel.Swyx [00:31:39]: Yeah.Akshat [00:31:40]: Yeah. I don't know if this is a natural follow-on to the topic of like my skepticism on distributed training is that while, like, people spend a lot of money on, like, cables to hook up GPUs, and even that is not, like, fast enough, and that's the bottleneck, is your networking fast enough?Swyx [00:31:59]: Yeah. So I guess you're talking about fully distributed training like, Dialog or something which is like cross data centerAkshat [00:32:06]: That would be, yes.Swyx [00:32:07]: That's the extreme.Akshat [00:32:08]: Yeah.Swyx [00:32:08]: You're in the middle, and then other people would have like the Mellanox cables up in, like, their actual data center.Akshat [00:32:14]: When you run multi-node training on Modal, RDMA, I think Mellanox, is, or InfiniBand is like a, is all seen as RDMA. but it's a way to bypass the TCP networking stack and, transfer, stuff much faster, between one node, to the other. And we have I think like 3 terabit per second, internal networkingSwyx [00:32:40]: OkayAkshat [00:32:40]: Which is the standard that's needed.Swyx [00:32:42]: Okay. So I misunderstood whatAkshat [00:32:43]: 50Swyx [00:32:43]: What part of the stack you wereAkshat [00:32:44]: 50 gigs overSwyx [00:32:45]: YeahAkshat [00:32:45]: If you wentSwyx [00:32:45]: YeahAkshat [00:32:46]: RDMA.Swyx [00:32:46]: Okay.Swyx [00:32:48]: Yeah. I, very impressive work.Multi-Node Training, Post-Training, and Auto ResearchSwyx [00:32:52]: So effectively you're extending like the model philosophy to the training cluster, like, yeah.Akshat [00:32:59]: Yeah. And we're, we're not going for like large scale training runs. the thing that we've built multi-node training for is, we see a lot of, smaller scale post-training. like, people are post-training like medium sized fund models, so they can, get higher quality on inference. this is a perfect fit, for something like that.Swyx [00:33:21]: Yeah. That is my impression of how a lot of these labs explore branches in post-training and then eventually merge whatever they find in.Akshat [00:33:31]: Yeah. The other use case we've seen for multi-node training is even if you have a big cluster, your researchers are still doing small runsSwyx [00:33:38]: YesAkshat [00:33:39]: Having elasticity thereSwyx [00:33:40]: Right, sureAkshat [00:33:40]: Matters a lot more.Swyx [00:33:41]: Yeah. the, like, this is like the current limiting factor for auto research, which is like you need to give your model some GPUs in order for it to completely run.Akshat [00:33:51]: We have a blog post on auto resource and model is,Swyx [00:33:55]: YeahAkshat [00:33:56]: Yeah, like, turns out to be pretty good substrate for that.Swyx [00:33:59]: So my impression is auto research means many things, likeAkshat [00:34:01]: YeahSwyx [00:34:01]: Anything that Andrej coins. Right now it's still science fair, right? Like not like, I don't know how many people are doing this.Akshat [00:34:08]: We're having a golf.Swyx [00:34:08]: Yeah.Akshat [00:34:09]: I thought the same thing.Swyx [00:34:11]: Yeah, you would know.Akshat [00:34:12]: We, like, our internal both training and inference teams use this the general shape of this quite a bit. like we have this one internal repo called auto inference, which essentially we've automated our own forward-deployed engineering efforts using, this harness, which is, the agent will just spin up a sweep of different things. It'll even run like, NVIDIA inside profiler and it'll like tweak configs and it'll arrive the right thing. it'll change your GPUs both from H200 to B200, and works really well.Swyx [00:34:47]: Nice.Akshat [00:34:47]: So yeah.Swyx [00:34:48]: By the way, I enjoy that your forward-deployed engineering is so technical that you have to do these things.Swyx [00:34:52]: It's very different from forward-deployed engineering from other people.Akshat [00:34:54]: Yeah. For our forward-deployed engineering team is, essentially they're like applied inference researchers or applied training researchers.Swyx [00:35:02]: Someone told me like they have to be able to build, but they also have to be able to sell. do they have to sell or are they like they're good, they're just like post-sale type of thing?Akshat [00:35:09]: It does, being able to talk to a customer and engage effectively with themSwyx [00:35:13]: YeahAkshat [00:35:13]: Matters a lot.Swyx [00:35:14]: They want the same thing.Akshat [00:35:15]: Yeah.Swyx [00:35:15]: ?Akshat [00:35:15]: But it's it's not really a sales, thing. We pair them with-- We have solution architects as well that are more on the sales side.Swyx [00:35:23]: Okay. Let's spend a bit more time on auto research. This is a big focus for for this year. Where does this go? like, have people explored enough? Like, there's all these beautiful charts of like improve and then level off a bit and then you find the next thing. Is this one abstraction up from normal training? Is that how we think about it, or do you think about it differently? Like model level training versus high, like driven hyperparameter search.Auto Inference and Modal BenchAkshat [00:35:51]: Yeah, like,Swyx [00:35:51]: Someone, some people call it like neural architecture search or whatever, right? Like.Akshat [00:35:54]: Yeah, - So the stuff I've seen people do with it is nowhere on the architecture level. It's pretty much tweaking parameters, but it's it's a hyperparameter sweep that's guided by some model intuition, so it's like much more efficient than, whatever other, sweep you would have.Swyx [00:36:12]: Yeah, it's just, it's just a question of where you want to spend your compute?Akshat [00:36:16]: Right.Swyx [00:36:16]: ‘Cause yeah, you can just throw infinite amounts of money on this and somehow you'll bang out Shakespeare?Akshat [00:36:22]: Yeah, infinite monkey.Swyx [00:36:24]: Yeah, so like the very good for model. and I think it's also very important that agents can spin up other agents, can spin up their infrastructure. Like very good for you. how good is our LLMs at generating model code? Like the benefit of existing LLMs is that you are in the data.Akshat [00:36:42]: Yeah. They're, they're surprisingly good. I think like pre Cloud 4 they were not, and then now they're able to shot, stuff out of the box. But we're playing around with releasing like a Modal Bench for like the harderSwyx [00:36:55]: YeahAkshat [00:36:55]: Things, that the LLMs cannot do yet and maybeSwyx [00:36:59]: What's an example of that?Akshat [00:37:01]: I think the things that- Sometimes agents struggle with, without right guidance and a skill is, how to, use the rest of our observability. Like how to. Something is failing, like how do you look at the logs and then update the right thing? It's reasoning about that. But they're able to shot, likeSwyx [00:37:23]: Yeah. You can just add a skill to it?Compute Strategy and Capacity PlanningAkshat [00:37:26]: Yeah. So we have a Modal skill now that. Which is why we built this Modal Bench. It's to find things like that, so we can address them in our tool.Swyx [00:37:35]: Tune a skill. Yeah.Akshat [00:37:36]: Yeah.Swyx [00:37:36]: No. it's it's good. are you facing any shortages? like we talk a lot about GPU shortages, but also CPU, also memory.Swyx [00:37:44]: Yeah.Akshat [00:37:45]: We have had a lot of growth, which means that, there's - we've had to be much better aboutSwyx [00:37:53]: PlanningAkshat [00:37:54]: Proactive capacity planning.Swyx [00:37:55]: Yeah.Akshat [00:37:55]: So we have,Swyx [00:37:57]: Which by the way, like it's like a MBA's like dreamAkshat [00:38:00]: YesSwyx [00:38:00]: Is like just planning this stuff. I think last time you and I talked about something maybe about this.Akshat [00:38:03]: Yeah. we have a really competent team of people that we call, The role is called compute strategy. so yeah, if anyone listening here or wants to work on thatSwyx [00:38:13]: Compute strategy?Akshat [00:38:13]: Yeah.Swyx [00:38:14]: I think,Akshat [00:38:14]: I feel like,Swyx [00:38:15]: I think the normies call it FP&A or something.Akshat [00:38:18]: Well, it's more It's it's not FP&A. It's it's There's a lot of interesting financial questions of like what is the blend between one year and three-year reservations? how do we forecast our own capacity? how do we. especially since our capacity is very fungible across different GPU types and different regions, like you have to model a lot of it. and you also have to have an opinion on how the supply chain is gonna evolve, and then you have to like, take bets,Swyx [00:38:49]: YeahAkshat [00:38:49]: Based on that.Swyx [00:38:50]: Tokenomics.Akshat [00:38:50]: Yeah.Swyx [00:38:51]: This is like probably a not a real point, but, I was trying to think about like what other industries. I was trying to think about like, we cannot be first to like these kinds of problems.Akshat [00:38:59]: Yeah.Swyx [00:39:00]: And what other industries have had this? And I was like, airlines with fuel and like they have to hedge their fuel and like, I think for a long time Southwest because they made like a hero fuel bet, they like were like super low cost becauseAkshat [00:39:12]: OhSwyx [00:39:12]: Compared to everyone else.Akshat [00:39:14]: Yeah. I hadn't thought about that.Vibhu [00:39:16]: We're at a fun time too?Akshat [00:39:18]: Yeah. It's. A lot of the compute business in general, for us is also about being very good about capacity management. That is how you have great unit, economics. but also over time it's how you can unlock more value for customers. Like, one of the things we're building now is like a way for customers to get, If they don't care about latency, like get much cheaper pricing and they'll get results back in like next 24 hours or something, like a batch tier essentially.Batch Tiers and Latency-Insensitive WorkloadsSwyx [00:39:47]: Yeah.Akshat [00:39:47]: And those are levers we have because we control the whole stack and scheduling and whatnot to give people a sufficientSwyx [00:39:53]: Yeah. I feel like they're not as popular. Like those, like the Frontier Labs have all those APIs. They're not as popular as they should be.Akshat [00:40:00]: The demand that we see for something like that is not for LLMs. although sometimes people wanna run evals andSwyx [00:40:08]: OkayAkshat [00:40:08]: Synthetic data prep and there it makes sense.Swyx [00:40:10]: Okay.Akshat [00:40:11]: But it's from a lot of LLM companies, like people who are doing computational bio, like they have to run really big batch jobs and they don't care about when they get it back.Swyx [00:40:22]: Yeah. And like they have a reasonable. It's it's also like a cousin to the stopping problem of like, will this finish in time?Akshat [00:40:30]: Yeah. You can bound it.Swyx [00:40:33]: Yeah.Akshat [00:40:33]: Like you can give peopleSwyx [00:40:34]: YeahAkshat [00:40:34]: SLAs on it.Swyx [00:40:35]: Yeah. I think what's, what's interesting is like the next phase of model.Swyx [00:40:38]: Like what, do people expect from you, now that you're established and you're like well-known compute player among all these leading companies. You had an inference launch week, and we talked a little bit about the launches. like what else? Like what else should people know?What Modal Builds NextAkshat [00:40:55]: We are building primitives that make our users' lives much easier. So, I think for example, with LLM inference, thousands more companies are gonna post-train their own models and, deploy open source models for inference. so we're thinking a lot about what is the best product shape for that. And, that involves everything from our training gym to, then, endpoints that get frontier-level performance. again, but I haven't talked to anyone. It looks somewhat different on other verticals. Like, we're also seeing a lot of real-time, audio-video stuff in there, which is why like, we're working on things like regional routing, with fallbacks. So you can get GPUs that are as close to users as possible. so you get like low latency for video streaming and whatnot. And then on the agent side, it's,Akshat [00:41:52]: We're still working very closely with our customers because stuff is changing so fast in terms of what they need. And, I think beyond sandboxes and persistent file systems, there's a lot of other things people will need from this agent stack as they build production agents. So yeah, we're thinking about those other things that fit in there.Swyx [00:42:13]: I want to ask what the other things are.Akshat [00:42:15]: Yeah. I probably should share right now.Swyx [00:42:17]: I think-- I think, okay, so, I do think a lot about the principal components of cloud, and you do talk about compute storage networking.Akshat [00:42:25]: Yeah.Swyx [00:42:25]: Because so far for me, it's fine. so far for the. the first couple generations of cloud, it's fine. What's different, qualitatively different about agents that you need some new permission level? Like a lot of people, okay, and I'll just kinda spew tokens at you until it like hopefully sparks something.Akshat [00:42:43]: Yeah.Swyx [00:42:44]: Like the new level now is whatever Claude Code does, which is dangerously scope permissions or like allow list by command or like whatever, right? And sometimes they're like, “Well, okay, we have like this adaptive thinking mode where like, just trust me, bro. I will make the calls for you.” Is that it? like mediated permissions.Hard Guardrails vs. LLM-Mediated PermissionsVibhu [00:43:03]: Now you're looping it with a goal and letting it roll.Akshat [00:43:06]: Yeah, I'm, I'm skeptical of LLM media permission for stuff that is at the sandbox level because you do want hard boundaries.Swyx [00:43:16]: Yeah.Akshat [00:43:16]: Otherwise, someone can exfiltrate stuff.Swyx [00:43:20]: But likeAkshat [00:43:20]: YeahSwyx [00:43:20]: Maybe that's old school thinking. Maybe we're the dinosaurs.Swyx [00:43:23]: Maybe the AI OS or the LLM OS is really the kernel is a goddamn LLM.Swyx [00:43:30]: Like it makes you feel uncomfortable.Akshat [00:43:31]: Yeah, I'm, I'm toldSwyx [00:43:32]: But that's what trusting the LLM is. Like imagine a spherical cow perfect LLM.Akshat [00:43:36]: Right.Swyx [00:43:37]: That it.Akshat [00:43:39]: Maybe.Swyx [00:43:41]: I wanna test the boundaries, right?Akshat [00:43:42]: Yeah.Swyx [00:43:42]: Like, and I don't believe that, but I wanna see where I'm wrong ‘cause that's, that's the consensus.Akshat [00:43:49]: Yeah. I think you always need hard guardrails when you want, And you can pair those with softer guardrails, right? And that's gonna be a lot of mediated.Managed Agents and Specialized SandboxesSwyx [00:44:00]: There. I'll also get you a end with a couple of your commentary on like the ecosystem outside of Modal. Manage agents. Everyone has one. Gemini, OpenAI, Claude, very useful for you, but also like it is their way of starting to edge into your space.Akshat [00:44:17]: Yeah.Swyx [00:44:17]: What's going on?Akshat [00:44:19]: Yeah, we're, very excited to partner with Anthropic and some of the other foundation labs, will not name who we're also working with. the way we see it is the manage agent thing is a great place to start if you're starting out building an agent and, But then when you get to, building something more production grade, like you're a company that's like Ramp that's building their own, Ramp also runs their accounting agent on us, so their external-facing agent. You need a lot more control over, your compute primitive on things like, what sort - how do you persist different files that the agent has access to, and how do you snapshot and restore? How do you control the networking? maybe you want GPUs. When you get to that point, you kinda want, a specialized sandbox provider, that gives you those things, and that's the role that we are trying to play.Swyx [00:45:15]: YeahAkshat [00:45:16]: We don't really have an opinion on the harness, whether it runs - it's a cloud-managed agent, and you hook it up to Model Sandbox, or you run the harness in Model Sandbox. We'll see where people converge with that.Swyx [00:45:26]: Yeah. Do you any opinions on like the meta harnesses, or just another layer on top of these things?Akshat [00:45:31]: You mean like the OpenPipeSwyx [00:45:33]: OpenPipe is one. I think Vercel had one, which I can't remember the name of right now. Fredshot had one. and then, to me, most recently was Data Databricks that had Omnigen. All these are meta harness. Like it's kinda pseudo agent cloud type things.Akshat [00:45:50]: I personally have not played around with them.Swyx [00:45:53]: Yeah.Akshat [00:45:53]: Build agents with them.Swyx [00:45:54]: Everything's bullish Modal, as long as it consumes more infra.Akshat [00:45:57]: That's why we're focusing on the infra layer. It's somewhere where our, relative competence is and, also it's a hard problem to solve.Swyx [00:46:06]: Yeah. I will say like just generally reflecting on that, I don't know if - if there's other topics on Modal, but like just generally reflecting as an infra person, not as intense as you, but in that field, this has like been the most exciting time in infra. Like it was boring for a while, and you couldn't really get people excited about data infrastructure. Like Eric would get on Data Console, everyone just watched the video and like say, “Look at how many sandboxes I can spin up,” and no one gave a crap.Why Infrastructure Became Exciting AgainAkshat [00:46:39]: Yeah.Swyx [00:46:40]: And like now everyone gives a crap.Akshat [00:46:42]: That's true. It is a very exciting time, and I think a lot of that's driven by just the amount of scale all of this stuff needs.Swyx [00:46:50]: I think the, like a lot of your initiatives or a lot of your like product directions make sense in retrospect, which is like the best kind, but I wouldn't necessarily have thought about it myself, which.Akshat [00:47:00]: We need the predictions.Swyx [00:47:02]: I think there's a lot that you just don't even see, right? Like you have the batch, you have the voice, you have the multimodal, but what else?Akshat [00:47:10]: What else is coming up for usSwyx [00:47:11]: Yeah. Where do you see things going?Akshat [00:47:13]: Yeah. I, in generalBiotech, Robotics, and Non-LLM AI WorkloadsAkshat [00:47:15]: It's it's clear that there's there's a huge shift happening. I think one thing that's not as obvious to people because LLM inference gets talked about so much and is also we work a lot of companies that are, doing things like drug discovery and computational bio, like the Chai Discoveries of the world. Big things are probably gonna happen there. we work a lot of robotics companies that are putting robots in like active deployments and getting good results out of them.Swyx [00:47:45]: Is there Air Gap Modal? Is there a version that is like prem air gapped whatever?Akshat [00:47:50]: No. We,Swyx [00:47:51]: You should cloud only.Akshat [00:47:51]: Yeah.Swyx [00:47:52]: Yeah. Okay. But yeah, so what you're saying is like because you're focused on primitives and they're good primitives, you find use cases in all these kinds of things.Akshat [00:48:01]: Yeah.Swyx [00:48:01]: Probably diversifies you a little bit away from LMS all the time.Akshat [00:48:05]: Yeah, absolutely. We're, we'- our goal isn't to only serve the LLM inference market.Swyx [00:48:10]: There are a lot just on the website, the audio,Akshat [00:48:12]: Yeah. We said both onSwyx [00:48:14]: Computational bio images. Yeah, there's a lot here. There's QTA TTS, customizing. Oh, Chatterbox. there was customizing Whisper.Akshat [00:48:24]: Okay. Yeah.Swyx [00:48:25]: This screen reminds me of a fallen competitor, which Replicate.Model APIs vs. Differentiated AI ProductsSwyx [00:48:31]: What's your postmortem on what happened?Akshat [00:48:34]: This is one thing we've stayed away from is providing an API for models because I think providing model APIs is some of it ends up serving like a really hobbyist market, which is much less sticky.Swyx [00:48:50]: Yeah.Akshat [00:48:50]: And we've always wanted to build for companies that are building products and need more flexibility that's not just an API.Swyx [00:48:57]: Which you can build an API for a model and this is clearly what it is. But you - but what you're saying, you can wrap it into a more fully functioning back end that you run.Akshat [00:49:06]: Yeah. So all of our examples, it's not that spin up this model, here's an API token, use it. They're all code.Swyx [00:49:13]: Okay.Akshat [00:49:13]: And so the point is that this is just an example.Swyx [00:49:16]: Starter code.Akshat [00:49:17]: Yeah. But you can tweak it however you want.Swyx [00:49:20]: Yeah.Akshat [00:49:21]: And if you're like a company building a product, like, computational bio whatnot, yeah.Swyx [00:49:26]: I guess I'm trying to tease out for listenersAkshat [00:49:28]: YeahSwyx [00:49:28]: When does it stop becoming, oh, you're just an API call and you're just a wrapper on API to becoming what you call a product, right?Swyx [00:49:36]: Like, what is that layer? Like what-- Like, more lines of code, but like beyond that, what is the substance that people add that qualifies it to be something more?Akshat [00:49:46]: I think there's a little bit of like a selection effect of like a lot of the companies who do wanna get deeper into that level are probably building something that's more differentiated. And, I think, an example is like - with LLM inference, originally we, worked with companies that were building their own post-training frameworks or they were, - Ramp early in the day was training their own tokenizer and like swapping out the tokenizer in Llama and whatnot. I'm not saying that's, that successful, in that case. But a better example is like, let's say Suno. because Suno, does not use Modal for training.Swyx [00:50:26]: Mikey on the pod. Yeah.Akshat [00:50:27]: But they use Modal for all their inference and that's because they have like a custom-- They have completely custom model architecture and that means that they have to be at the code level and tweak things that are not, just an API.Swyx [00:50:41]: It's interesting as well, like we had, Ethan, most recently on the xAI Groq team make a prediction that like the next tier in video gen is not a better video model, it's a better model or agent that orchestrates video models.Video Agents and Production WorkflowsAkshat [00:50:56]: Oh, interesting.Vibhu [00:50:56]: Language model backbone that can use toolsAkshat [00:50:58]: RightVibhu [00:50:59]: And write code.Akshat [00:51:00]: Like, yes, I can make my second video or my second video from Groq, but I want my minute video.Akshat [00:51:06]: And I'm not going there through normal video gen.Swyx [00:51:10]: Yeah, that's interesting. I - So we have GPU sandboxes and recently have seen a few companies doing agents that do video manipulation or,Akshat [00:51:22]: Yeah. Give it FFmpeg and just do it.Swyx [00:51:23]: Run FFmpeg. But likeAkshat [00:51:25]: That's not enough.Swyx [00:51:25]: Yeah.Akshat [00:51:26]: You need to give it Adobe.Swyx [00:51:27]: Yeah, I hadn't put it together with like it would be a video production thing. in my mind these things were going more towards editingAkshat [00:51:36]: Yeah.Vibhu [00:51:36]: Well, shout out Mantis.Akshat [00:51:37]: I think about this a lot.Swyx [00:51:38]: .Akshat [00:51:41]: Yeah. Sorry.Vibhu [00:51:41]: Luma. Luma Agent is a version of this for video production, but it's a off.Swyx [00:51:46]: I was gonna get your quick takes, on some other stuff that happensGitpod/Ona, CI, and Runtime SandboxesSwyx [00:51:50]: In recent news and just-just see if you have anything interesting. Gitpod, very li

Cross-border freight transported via the China-Laos Railway has exceeded 20 million metric tons since the line opened in December 2021. As of Wednesday morning, the railway has operated over 23,000 cross-border freight trips.

Hello sleepy listeners & welcome!SPECIAL ANNOUNCEMENTStarting this weekend, I am launching Drift Back Sundays! Every Sunday night, I will unlock a favorite cozy classic from my archive to help you ease into the workweek. Keep an eye on your feed this Sunday for a beloved favorite!Tonight, we begin the timeless classic The Railway Children by E. Nesbit.This beloved story follows three siblings whose comfortable lives are suddenly turned upside down, leading them to a quiet cottage in the countryside where unexpected friendships, small adventures, and acts of kindness begin to shape their new world. Filled with warmth, hope, and gentle moments, it's the perfect story to unwind with at the end of the day.Now, make yourself comfortable, relax, and I hope you enjoy the story :)Sweet dreams,JoanneThis podcast is 100% listener-supported, completely ad-free, and made possible by wonderful listeners like you. Thank you for helping me keep bedtime a peaceful place.If you'd simply like to make a one-time contribution to help support the podcast, you can do so here: https://driftoff.supercast.com/donations/new. Every gift, no matter the size, is deeply appreciated and helps me continue creating peaceful stories for you.If you'd like even more relaxing stories throughout the week, Drift Off Premium includes:• Fresh new premium episodes every Tuesday & Thursday• Instant access to the complete premium archive• Intro-free listening so you can dive straight into your wind down• Listen first, months—or even years—before the public feed• An exclusive full-length audiobook libraryYou can learn more by visiting www.driftoffpodcast.com, where you'll also find my downloadable audiobooks, my Dream Shop, and everything else happening in the world of Drift Off. Thank you for being here, and for helping keep Drift Off a peaceful, ad-free space. 

Mount Washington became the location of one of the deadliest accidents in American Railroad history in 1967. Home to the world's first Cog Railway, a routine descent turned catastrophic when the locomotive left the tracks, sending a passenger car full of tourists into a terrifying runaway ride down one of the steepest railroad grades in the world. For a full list of our sources, visit npadpodcast.com/episodes For the latest NPAD updates, group travel details, merch and more, follow us on npadpodcast.com and our socials: Instagram: @‌nationalparkafterdarkTikTok: @‌nationalparkafterdark Support the show by becoming an Outsider and receive ad free listening, bonus content and more on Patreon or Apple Podcasts. Want to see our faces? Catch full episodes on our YouTube Page! Thank you to this week's partners! Ka'Chava: Go to https://kachava.com and use code NPAD for 15% off your first order. ButcherBox: As an exclusive offer, new listeners can get their choice of free ribeyes for a year, or ground beef or chicken breast for life, PLUS $20 off their first box. Visit http://ButcherBox.com/NPAD  to claim your offer. HelloFresh: Get 10 Free Meals + Free Breakfast for Life with HelloFresh! Go to http://HelloFresh.com/npad10fm. IQBAR: Get 20% off all IQBAR products plus FREE shipping by texting PARK to 64000. BetterHelp: Start therapy today and get 10% off your first month at http://BetterHelp.com/NPAD Learn more about your ad choices. Visit podcastchoices.com/adchoices

1. China's Qingzhou cargo spacecraft test vehicle releases second batch of scientific achievements 2. China expects to see 1.01 bln railway trips during summer travel rush 3. Chinese astronomers detect radio pulses from long-silent neutron star 4. China launches sea-river intermodal zero-carbon shipping route

The West Clare Railway Greenway is on track after Clare County Council submitted the first section of the project to An Coimisiún Pleanála for development. Alan Farrell, Deputy Chief Executive and Director of Service for Housing at Clare County Council.

The builders of the Qinghai-Xizang Railway endured extreme cold, high altitudes, and immense hardship to complete what is now the world's highest-altitude railway. Two decades later, this engineering landmark has brought communities closer together, expanded access to travel, and reshaped life across Xizang. In this special episode of The Hub, Wang Guan and South African influencer Lara Netherlands travel from Xining to Lhasa aboard the iconic railway as it marks 20 years of operation.

It's being argued that the West Clare Railway Greenway could be "bigger than Moneypoint" in terms of its economic impact. Clare County Council has confirmed its submitting the first section of the long-awaited project to An Coimisiún Pleánala for development consent. The local authority has also commenced steps to acquire lands for the Kilrush to Kilkee stretch. Kilrush Independent Councillor Ian Lynch believes the knock-on effect of the greenway can't be understated.

Day 1,586.Today, as Vladimir Putin continues to make grossly exaggerated claims about Russia's gains on the battlefield, we assess the latest military progress of both sides, before looking at the long-delayed and controversial defence investment plan finally announced by the British. More money for drones, autonomous systems, and artificial intelligence: but does it go far enough, and how close is London to hitting the 5% NATO target demanded by President Donald Trump? Then we hear what the citizens of Kyiv think about Ukraine being on the pathway to membership of the European Union, and report on a manhunt underway in southern France after a parcel bomb exploded at a residential building in neighbouring Monaco, injuring wealthy Ukrainian businessman Vadym Yermolaiev.Contributors:Francis Dearnley (Host on Ukraine: The Latest). @FrancisDearnley on X.Dominic Nicholls (Host on Ukraine: The Latest). @DomNicholls on X.James Crisp (Telegraph's Europe Editor). @JamesCrisp6 on X.Antonia Langford (Freelance Journalist in Kyiv). @Antonialford on XProducer: Phil AtkinsSenior Producer: Lilian FawcettVideo Producer: Sophie O'SullivanSocial Producer: Gabby ColvinStudio Director: Meghan SearleExecutive Editor: Francis DearnleyCreated by David KnowlesNOW IN FULL VIDEO WITH MAPS & BATTLEFIELD FOOTAGE:Every episode is now available on our YouTube channel shortly after the release of the audio version. You will find it here: https://www.youtube.com/@UkraineTheLatest CONTENT REFERENCED:Listen to our sister podcast Iran: The Latest:Video: https://www.youtube.com/playlist?list=PLJnf_DDTfIVAif-vifC6F2aoPB8GIw6dk Apple: https://podcasts.apple.com/gb/podcast/iran-the-latest/id1712903296 Spotify: https://open.spotify.com/show/7gPBO0qnZI1YBi25zaVT1cThe battle to bring Europe's biggest military into the EU (James Crisp, Antonia Langford and Joe Barnes for The Telegraph)https://www.telegraph.co.uk/world-news/2026/06/24/the-battle-to-bring-europes-biggest-military-into-the-eu/ Ukrainian tycoon injured in Monaco bombing (The Telegraph):https://www.telegraph.co.uk/world-news/2026/06/29/monaco-house-explosion-three-injured/ Meduza has identified over a thousand war veterans who have already received positions within the Russian government (Meduza, in Russian):https://meduza.io/feature/2026/06/29/novaya-rossiyskaya-elita EMAIL US:Contact the team on ukrainepod@telegraph.co.uk. We continue to read every message, and seek to respond to as many as possible.Thumbnail image credit: Defense Intelligence of Ukraine (DIU)HIGHLIGHTS:Ukraine blows up railway bridges and Russian space centreUK claims army will be '10 times more lethal' as new defence plan revealed Hosted on Acast. See acast.com/privacy for more information.

Let's conclude our month of travels with more from this helpful yet somewhat snarky guide to riding that newfangled device, the steam train. This time, advice for the journey itself, including how to read a book, have a chat, fall asleep, rush the snack bar, and avoid losing your head out the window. All aboard for sleep!   Help us stay ad-free and 100% listener-supported! Patreon: https://www.patreon.com/boringbookspod Buy Me a Coffee: https://www.buymeacoffee.com/d5kcMsW   Read "The Railway Traveller's Handy Book" at the Internet Archive: https://archive.org/details/railwaytraveller00unse   Music: "Healing" by Lee Rosevere, licensed under CC BY, https://leerosevere.bandcamp.com   If you'd like to suggest a copyright-free reading for soft-spoken relaxation to help you overcome insomnia, anxiety and other sleep issues, connect on our website, https://www.boringbookspod.com.

China's first railway linking Xizang to the national rail network has carried more than 104 million passengers and transported 824 million tons of cargo over the past 20 years.

In this episode of Brave New Bookshelf, hosts Steph Pajonas and Danica Favorite sit down with Joseph Ucuzoglu, a seasoned developer, author, and co-founder of the Future Fiction Academy, to explore the game-changing world of "vibe coding." Joseph shares how next-generation AI models are completely blurring the line between writer and software developer, empowering authors to build their own custom writing tools and applications using plain, natural language. From setting up a simple, no-code app-building pipeline using tools like Claude, Cursor, GitHub, and Railway, to leveraging consistent new image models for visual story planning, this conversation reveals how creatives can take ultimate control over their technology and workflows without needing a computer science degree. Visit our website https://bravenewbookshelf.com to view the full episode notes, links and apps mentioned in the episode, and the full transcript.

See omnystudio.com/listener for privacy information.

A Turkish-Saudi agreement to revive the Ottoman-era Hijaz Railway tells the story of geopolitical realignment in the wake of the wars in Gaza, Lebanon, and Iran, including the future of Iran's relations with the Gulf monarchies. The agreement is the tale of efforts to reduce regional dependence on the Strait of Hormuz, diverging Gulf attitudes towards cooperation with Israel, dashed US hopes of including Israel in a rail and shipping network that would connect the Gulf and India to Europe, diminished prospects for Saudi-Israeli diplomatic relations, Turkey's evolving regional ambitions, and post-Bashar al-Assad Syria's reintegration into regional dynamics. The agreement is also indicative of a broader shift in the wake of the Iran war towards alternative export routes and hardened critical infrastructure that will impact the Gulf's geopolitics.

When vulnerable Cornwall resident Steven Hoskin moved into his own flat in St Austell, he hoped for independence and friendship. Instead, a group of troubled young people entered his life, gradually taking over his home and exploiting his trusting nature. As warning signs mounted, opportunities to intervene were missed, with devastating consequences…*** LISTENER CAUTION IS ADVISED *** This episode was researched and written by Eileen Macfarlane.Script editing, additional writing, illustrations and production direction by Rosanna Fitton.Audio editing by Joel Porter at Dot Dot Dot Productions.Narration, additional audio editing and mixing, and script editing by Benjamin Fitton.To get early ad-free access, including Season 1, sign up for They Walk Among PLUS, available from Patreon or Apple Podcasts.More information and episode references can be found on our website https://theywalkamonguspodcast.comSOCIAL MEDIA: https://linktr.ee/TheyWalkAmongUsSupport this show http://supporter.acast.com/theywalkamongus. Hosted on Acast. See acast.com/privacy for more information.

Why are couples, wellness seekers, and travelers from around the world flocking to Santa Fe? Join travel expert, author and TV host Darley Newman as she explores the people, places, and experiences that have made Santa Fe County one of the Southwest's most captivating destinations. From weddings aboard Sky Railway and historic venues like El Rancho de las Golondrinas and Bonanza Creek Ranch to luxury escapes at Bishop's Lodge, Auberge Collection and Four Seasons Resort Rancho Encantado, discover why Santa Fe has become a top destination for romance and celebration. Along the way, Darley speaks with Game of Thrones creator George R.R. Martin aboard Sky Railway, explores Bonanza Creek Ranch where weddings and movie sets mix, learns about New Mexico's living history from Pedro Martinez at El Rancho de las Golondrinas, samples historic chocolate elixirs with Bonnie Bennett at Kakawa Chocolate House, and experiences wellness traditions at Ten Thousand Waves, Ojo Santa Fe, and Four Seasons Resort Rancho Encantado. From mountain sunsets and healing waters to historic railways and unforgettable landscapes, discover why so many visitors leave Santa Fe already planning their return.Get more trip itineraires, travel advice, Darley's Revolutionary Road Trip book and more at darley-newman.com 

Send us Fan MailIn this episode we are delighted to have been made so welcome at the Mornington Tourist Railway, a broad gauge railway in Victoria , Australia, as Mikey Cunningham rides the footplate and chats to Secretary Robert Read. Regular listeners will know most of us are based in the top left hand corner of Wales and at the same time Mikey was in Melbourne, volunteers from Queensland were working on the Welsh Highland Railway. Producer Laura Raymond catches up with Darrell McCulloch ,Mary Ann Martin, Ben Gardener and Chris Banks who are involved with the Mary Valley Rattler back home.Sharon Gregory visits her favourite London Undeground Stations - designed by architect Leslie Green.Ffestiniog Railway Volunteer Carol Younger tells us about her new life in 'Scarlets' as a Chelsea Pensioner – a prestigious army veteran role in the UK !Alasdair Stewart  goes to a wonderfully restored art deco railway station in Sussex ahead of the summer open days to meet the friends of Bishopstone Station. It is one of the only stations with gun emplacements in the UK!Social media content for Mornington Railway kindly produced by Sara Walker and can be viewed on our facebook pageLinks to the Railways and organisations mentioned in this episode below:Mornington Tourist RailwayMary Valley Rattler Leslie Green Tube Stations  - Tiles of the Unexpected by Douglas RoseFriends of BishopstoneThe Chelsea PensionersThe Ffestiniog and Welsh Highland RailwaysThis podcast is produced by Laura Raymond and presented by Alasdair Stewart and Sharon Gregory. Our 'Making Tracks' music is with kind permission of composer and musician Richard Durrant. It is a unique piece inspired by the rhythm of the historic rolling stock on the Ffestiniog Railway on the scenic journey from Harbour Station to Tan y Blwch. You can listen and download the full 'Tan y Bwlch' Ukulele Quartet here: Thank you to voice artist David King - for the Railway Ride outs voice over. Ukulele Quartet No. 1 "Tan y Bwlch"  Ukulele Quartet No. 1 "Tan y Bwlch" Richard Durrant · Single · 2019 · 3  songs.    

On this day, 22 June 1945, tens of thousands of workers in Nigeria defied the Trades Union Congress (TUC) and walked out on a general strike in protest at the British colonial administration refusing to meet workers' demands for a minimum wage of 2 shillings and sixpence and a 50% increase in the cost of living allowance. The TUC wanted to delay any action, but after months of agitation involving mass meetings of up to 8,000 workers at a time, the workers were not prepared to wait any longer. Railway employees, dockers and civil service workers walked out while many workers at private firms refused to cross picket lines. At its peak, between 42,000 and 200,000 workers were out, and despite the deployment of British troops and sabotage by some nationalist groups like the Nigeria Youth Movement the stoppage lasted 45 days. The strike was largely successful, as the cost of living increase was awarded in 1946, backdated to the previous year.More information, sources and map: https://stories.workingclasshistory.com/article/9494/Nigeria-general-strikeOur work is only possible because of support from you, our listeners on patreon. If you appreciate our work, please join us and access exclusive content and benefits at patreon.com/workingclasshistory.See all of our anniversaries each day, alongside sources and maps on the On This Day section of our Stories app: stories.workingclasshistory.com/date/todayBrowse all Stories by Date here on the Date index: https://stories.workingclasshistory.com/dateCheck out our Map of historical Stories: https://map.workingclasshistory.comCheck out books, posters, clothing and more in our online store, here: https://shop.workingclasshistory.comIf you enjoy this podcast, make sure to check out our flagship longform podcast, Working Class History

The Pere Marquette docks in Arcadia, Michigan, once connected a small Lake Michigan village to a much larger world. In this episode of End of the Road in Michigan, we follow the story of the harbor, railroad and steamship network that helped shape Arcadia during the late 1800s and early 1900s.Through rare historic postcards and local history, we examine how the Pere Marquette Railroad, the Arcadia & Betsey River Railway and Great Lakes steamers worked together to move lumber, freight, passengers and manufactured goods through this busy harbor. What began as a lumber town grew into a transportation hub where trains met ships and local products reached markets across the Great Lakes region.You'll learn about Henry Starke's role in building Arcadia, the creation of the channel connecting Bar Lake to Lake Michigan, the rise of the Starke Land & Lumber Company, the devastating 1906 sawmill fire and the town's transition into furniture manufacturing. We also look at the steamers that regularly called at Arcadia's docks and the people whose daily lives revolved around the waterfront.This episode offers a fascinating look at a forgotten chapter of Michigan transportation history and reveals how one small harbor played an important role in the economic growth of Northwest Michigan.If you enjoy stories about Michigan history, Great Lakes shipping, railroads, steamships, lumber towns and vintage postcards, be sure to follow End of the Road in Michigan for more journeys into the state's past.#MichiganHistory #ArcadiaMichigan #PereMarquette #GreatLakesHistory #RailroadHistoryThe End of the Road in Michigan is a production of Thumbwind Publications

In this episode of IPS Finance, we provide a beginner-friendly guide to investing in IPOs, explaining the application process, key factors to evaluate, and common mistakes investors should avoid. The discussion also compares the Railway and Defence sectors, examining their growth prospects, opportunities, and risks to help investors understand which sector may offer better potential. Additionally, we touch upon the impact of the US Dollar on markets and investment decisions. A practical and insightful episode designed to help both new and experienced investors make informed choices.

China's national railway network is expecting 83 million trips during the Dragon Boat Festival travel rush. Communities across the country are marking the festival with traditional activities such as dragon boat races and making Zongzi, or glutinous rice dimplings.

We've described some pretty fairly awful commutes on this show before. On today's very special "return-to-Africa" episode, all people wanted to do was get to work, but the weather got bad to the point where the road said "you shall not pass, your life is in danger". The train took a look at all this and said, "hold my beer”.On today's episode: you will learn how the location of today's story sounds toasty and hot to the uninitiated, but is actually one of the wettest places on earth; we will describe a claustrophobic and unenviable situation somewhere between the roller-skating in the back of the truck stunt from Jackass combined with the trash compactor scene from Star Wars; and I will actually say that no one choo choo chooses to be in today's kind of disaster, which I only call out early to ask for your forgiveness.And if you were listening on Patreon: you would learn about the US military's ambitions to turn its enemies into bee-coated, gay, diarrhea fanatics, and how they inspired Mikkos Cassadine's aims of destroying the world in the 1980s; we'll visit a place so rainy that you will have no choice but to assume I'm lying; and we'll walk through a list of all the different, awful things that can happen to your spine. Also, at the end of this episode, I'm going to announce the results of a naming contest we held for our hungry gorilla friend, and I will share the story behind it, which, fair warning, is extremely emotional.People describe travel by rail as a romantic way to see the landscape. Well, I don't know so much about that, but in this very special and intimate episode, a lot of people were brought closer together. I wanted to shout out Joyce Mokou Kontcheu (ask how to pronounce) who sent me my very first fan mail from Africa! That's a big deal for me. This was one of those rare occasions where a starter disaster perfectly sets the stage for a much worse secondary disaster. I call it a cascading infrastructure failure. She called it a careless disaster that could have been avoided with a little common sense. She truly hoped I would cover it, so yes, of course I did. Merci, Joyce.And I didn't have time to record a quick thing for our June Birthdays, so I wanted to shout out Charles Jewell and Kerry Ann Borthwick for another year around spinning around the sun in an otherwise cold and indifferent universe, wishing them a little birthday cheer, and thanks again to Hydra Corvi again for helping me with a little research on this one. From here we're back in my hometown just long enough to make a little fun of the World Cup before jetting off to beautiful Corsica to watch the beautiful game and have a high statical chance of getting very, very hurt. Spoiler, in the safety segment, I'm going to tell you what to do if not-only are you impaled on a pole, but suspended above the ground by it like a bug pinned to a wall. Good stuff.––––– THANK YOU. Most shows survive at the whim of production companies and corporate sponsors, built from the top down. Doomsday doesn't exist because some network exec believes in it – it exists because actual people do. It's built from the bottom up, and it's been my privilege to bring you these stories. Just you, me, and a microphone.  I don't do this for you, so much as I do this because of you. If you'd like to support the show at Buy Me A Coffee, or join the club over at Patreon for AD-FREE EPISODES, LONGER EPISODES, EXTRA CONTENT, all that good stuff All older episodes can be found on any of your favorite channels   Apple : https://tinyurl.com/5fnbumdw Spotify : https://tinyurl.com/73tb3uuw IHeartRadio : https://tinyurl.com/vwczpv5j Podchaser : https://tinyurl.com/263kda6w Stitcher : https://tinyurl.com/mcyxt6vw Google : https://tinyurl.com/3fjfxatt Spreaker : https://tinyurl.com/fm5y22su RadioPublic : https://tinyurl.com/w67b4kec PocketCasts. : https://pca.st/ef1165v3 CastBox : https://tinyurl.com/4xjpptdr Breaker. : https://tinyurl.com/4cbpfayt Deezer. : https://tinyurl.com/5nmexvwt  Follow us on the socials for more Facebook : www.facebook.com/doomsdaypodcast Instagram : www.instagram.com/doomsdaypodcast Twitter : www.twitter.com/doomsdaypodcast TikTok : https://www.tiktok.com/@doomsday.the.podcast Safety google off. We'll talk soon. And thanks for listening. Become a supporter of this podcast: https://www.spreaker.com/podcast/doomsday-history-s-most-dangerous-podcast--4866335/support.

The completed station was formally opened for use on 29 May 1854 to link London with the west of England and South Wales, reflecting the broader growth of rail transport during the mid-nineteenth ...

In the early nineteenth century, engineers discovered that steam power and iron rails could be combined to move people and goods faster than any horse or ox could. Within a few decades, railways had spread across every continent. Cities were reorganised around stations, clocks were synchronised, leisure and luxury were redefined, and entire economies began to run according to railway timetables. This was the Golden Age of the railways — a period when steam and steel transformed landscapes and fundamentally altered the way the world worked.  But how did a strange experimental machine become the backbone of modern life? How did railways reshape everything from holidays, to warfare, to time itself? And why, long after the steam age ended, does so much of modern life still run on railway logic? This is a Short History Of the Golden Age of Railways. A Noiser podcast production. Hosted by John Hopkins. With thanks to Christian Wolmar, a writer and broadcaster specialising in transport, and author of several books on the history of the railways. Written by Sean Coleman | Produced by Kate Simants | Production Assistant: Chris McDonald | Exec produced by Katrina Hughes | Sound supervisor: Tom Pink | Sound design by Oliver Sanders | Assembly edit by Dorry Macaulay | Compositions by Oliver Baines, Dorry Macaulay, Tom Pink | Mix & mastering: Cody Reynolds-Shaw Unlock the next two episodes of Short History Of… right now by subscribing to Noiser+. You'll also get ad-free listening and early access to shows across the Noiser podcast network, including Real Survival Stories and Sherlock Holmes Short Stories. Just click the subscription banner at the top of the feed, or head to www.noiser.com/subscriptions to get started. ⁠A Short History of Ancient Rome⁠ - the debut book from the Noiser Network is out now! Discover the epic rise and fall of Rome like never before. Pick up your copy now at your local bookstore or visit ⁠⁠noiser.com/books⁠⁠ to learn more. Learn more about your ad choices. Visit podcastchoices.com/adchoices