Podcasts about Mac

Leaks point to a busy October for Apple with a new Apple TV, HomePod mini, and Home Hub launching in tandem with the iPhone Duo. Here are the latest rumors and more on the AppleInsider Podcast. Contact your hosts:@williamgallagher_ on Threads@WGallagher on TwitterWilliam's 58keys on YouTubeWilliam Gallagher on emailWes on BlueskyWes Hilliard on emailWes's blog HillitechSponsored by:Origin Technology: Origin is endpoint AI observability. See what a trace looks like at originhq.com/appleinsiderLinks from the Show:iPhone 18 Pro Max reviewM5 Max Mac Studio review: Far better choice than Ultra for most desks'Get Ready' to pre-order the iPhone Duo starting October 12Unsurprisingly, Meta's Muse AI agent blatantly ignores user permissionsChatGPT as an extension in Siri dramatically underperformed, says OpenAINew Apple TV 4K leak confirms a very familiar form factoriPad mini finally getting FaceTime camera move, leak suggestsApple's next HomePod mini won't get a redesign, but will get some new colorsApple Intelligence is coming to the the next entry-level iPadApple's spatial computing strategy was on full display at Meta ConnectApple's smart glasses predicted for 2027, upgraded Apple Vision Pro 2028Apple Vision Pro's development graveyard exemplifies Apple's '1,000 no's to every yes'Apple's US staff will get extended Thanksgiving break under Ternus tooSnoopy & Fraggles getting new holiday specials on Apple TVHow to watch 'It's the Great Pumpkin, Charlie Brown' for free in 2026Small layoffs and budget cuts are hitting Apple, with more expectedApple Watch Ultra 4 review: An Support the show:Support the show on Patreon or Apple Podcasts to get ad-free episodes every week, access to our private Discord channel, and early release of the show! We would also appreciate a 5-star rating and review in Apple PodcastsMore AppleInsider podcastsTune in to our HomeKit Insider podcast covering the latest news, products, apps and everything HomeKit related. Subscribe in Apple Podcasts, Overcast, or just search for HomeKit Insider wherever you get your podcasts.Subscribe and listen to our AppleInsider Daily podcast for the latest Apple news Monday through Friday. You can find it on Apple Podcasts, Overcast, or anywhere you listen to podcasts.Those interested in sponsoring the show can reach out to us at: advertising@appleinsider.com ★ Support this podcast on Patreon ★

Listen to a recap of the top stories of the day from 9to5Mac. 9to5Mac Daily is available on iTunes and Apple's Podcasts app, Stitcher, TuneIn, Google Play, or through our dedicated RSS feed for Overcast and other podcast players. Sponsored by Stuff:Stuff helps you get everything out of your head and into a simple, elegant system—closing open loops and reducing mental stress. A simple to-do list for iPhone, iPad, and Mac, with powerful tools that make organizing, tracking, and checking off your tasks a whole lot more satisfying. Get Stuff done. New episodes of 9to5Mac Daily are recorded every weekday. Subscribe to our podcast in Apple Podcast or your favorite podcast player to guarantee new episodes are delivered as soon as they're available. Stories discussed in this episode: New MacBook Pro redesign gets exciting launch timing update Apple has a new MacBook Pro coming soon, here's what we know Apple says iPhone Duo has ‘replaceable' folding display layer to minimize crease ‘HomePad' could launch in these four colors, per leaker The iPhone 18 Pro is selling well in China for three reasons Listen & Subscribe: Apple Podcasts Overcast RSS Spotify TuneIn Google Podcasts Subscribe to support Chance directly with 9to5Mac Daily Plus and unlock: Ad-free versions of every episode Bonus content Drop us a line at happyhour@9to5mac.com. You can also rate us in Apple Podcasts or recommend us in Overcast to help more people discover the show.

The 8am hour of Friday's Mac & Cube continued with Week 5 of MAXX BALL Friday!! We began with Ohio State vs. Iowa & Kentucky vs. South Carolina; then, the guys continue with Miami vs. Clemson and Washington vs. USC; and finally, Cole & Greg go MAXX BALL on Arkansas vs. Texas A&M. "McElroy & Cubelic In The Morning" airs 7am-10am weekdays on WJOX-94.5!!See omnystudio.com/listener for privacy information.

Friday's 7am hour of Mac & Cube kicked off Week 5 of MAXX BALL Friday!! First up, it's Alabama vs. Mississippi State & Florida vs. Missouri; then, the guys get into Auburn vs. Tennessee; later, Stanford Steve, from College Gameday & SportsCenter w/SVP, offers winners for Week 5 & give his thoughts on the bigger games this weekend; and finally, Cole & Greg go MAXX BALL on Notre Dame vs. North Carolina. "McElroy & Cubelic In The Morning" airs 7am-10am weekdays on WJOX-94.5!!See omnystudio.com/listener for privacy information.

Friday's 9am hour of Mac & Cube rolled on with more Week 5 of MAXX BALL Friday!! Right out the gate, we put our official predictions on the record for a bunch of Week 5 contests; later, Geoff Collins, former GT head coach and former Miss State DC, previews the Alabama vs. Miss State game, lays out how he'd defend each team & says which defense has the advantage in Auburn-Tennessee; and finally, we reveal our TV watching plans, thanks to TD's Fine Furniture in Sumiton. "McElroy & Cubelic In The Morning" airs 7am-10am weekdays on WJOX-94.5!!See omnystudio.com/listener for privacy information.

The Geeks return with a brand-new Grumpy Old Geeks Wiki containing 21,577 static HTML pages, because apparently the appropriate response to having a massive podcast archive is to build an even more massive searchable monument to it. From there, things get considerably less wholesome as they dig into TikTok's settlement with Alabama, AI companies promising safeguards while simultaneously unleashing increasingly autonomous agents, and an OpenAI agent that apparently decided that “I can't access this” meant “perhaps I should hack it.” Government websites, a university digital library, and other targets apparently became irresistible once the normal route to the information stopped working. The Geeks contemplate the exciting future of digital interns who don't understand that the Computer Fraud and Abuse Act is, in fact, not a suggestion.The AI-agent discussion rolls into Meta's Muse, OpenAI's new agent tools, security boundaries, and the increasingly familiar problem of giving software enough permissions to accomplish a task and then discovering it has developed its own interpretation of “accomplish.” The episode also tackles Utah's attempt to apply age verification requirements to VPN users, New York's legal fight with prediction markets, Meta expanding Instagram into schools, and the continuing saga of AI-generated music and copyright. Then there's Automatic's corporate drama involving Matt Mullenweg, vibe coding, and the increasingly compelling argument that if you can build a website in a few hours, maybe spending years arguing about WordPress is no longer the best use of anyone's time.Finally, the Geeks move on to the technological disasters that really matter: Plex changing the Apple TV skip controls unless you pay for premium, a Samsung software update that managed to turn some AI refrigerators into very expensive food-warming cabinets, and Toy Story 5 proving once again that Hollywood has never met a perfectly good ending it couldn't monetize. There's also a trio of soccer documentaries, including Italia 90, Angel City, and Game and Glory; a discussion of the Strange New Worlds finale “Tomorrow's Enterprise”; and Meta's new lightweight VR glasses. Because nothing says “we have learned absolutely nothing” quite like putting more software between you and your refrigerator.Sponsors:DeleteMe - Get 20% off your DeleteMe plan when you go to JoinDeleteMe.com/GOG and use promo code GOG at checkout.Private Internet Access - Go to GOG.Show/vpn and sign up today. For a limited time only, you can get OUR favorite VPN for as little as $2.03 a month.SetApp - With a single monthly subscription you get 240+ apps for your Mac. Go to SetApp and get started today!!!1Password - Get a great deal on the only password manager recommended by Grumpy Old Geeks! gog.show/1passwordShow notes at https://gog.show/765Watch on YouTube at https://youtu.be/meLT-1PRbpASHOW NOTESThe Grumpy Old Geeks WikiTikTok reaches first state settlement over teen safety claims, agrees to user limitsLawyers in Alabama's TikTok settlement set to earn $14 millionBill Gates says it's 'completely irresponsible' for AI to not have safeguardsOpenAI's agent hacked into an Australian government websiteOpenAI's agents targeted and infiltrated US government websitesOpenAI Gets Sued Over the Hugging Face HackWith Dots, OpenAI Wants You to Stop Being Afraid of Its AI AgentsTrump's New America.gov Chatbot Seems to Drop Acid When You Tell It to Play MinecraftNVIDIA Launches Open Agent Safety Platform to Secure Agents From Testing to DeploymentHere's why OpenAI is absent from Nvidia's industry-wide effort to end rogue AI agentsFederal Judge Blocks Utah's VPN CrackdownNew York continues to fight prediction markets with a lawsuit against PolymarketExpanding Instagram's School Partnership Program to Help Teens Stay InformedAutomattic has a new board after failed attempt to put CEO on leaveThe problem with smart appliances: some of Samsung's AI fridges have shut down and lost their cool after a bad update was accidentally pushed to themToy Story 5Italia 90Angel CityGame and GloryStar Trek Strange New Worlds S04E10 Tomorrows EnterpriseThe DiplomatCan Imax, Dolby and New VR Glasses Help Meta Reboot Its Immersive Entertainment Ambitions?Peter Byrne, Singer From '80s Synth-Pop Duo Naked Eyes, Dies at 74See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

It's time to podcast about video games and the people who love them once again, this week touching on more time with Control Resonant, End of Abyss, and playing American Truck Simulator in (gasp) something other than a truck. Also, Xbox swears Xbox isn't for sale, more Last of Us may be coming in some form, we unpack the essential qualities of a good Metroidvania, and more.CHAPTERS(00:00:00) NOTE: Some timecodes may be inaccurate for versions other than the ad-free Patreon version due to dynamic ad insertions. Please use caution if skipping around to avoid spoilers. Thanks for listening.(00:00:10) Intro(00:00:57) Some venting about text messaging without a smart phone(00:20:40) End of Abyss  |  [Xbox Series X|S, PlayStation 5, PC (Microsoft Windows)]  |  Oct 01, 2026(00:41:38) First Break(00:41:38) Control Resonant  |  [Mac, PC (Microsoft Windows), PlayStation 5, Xbox Series X|S]  |  Sep 24, 2026(00:56:20) American Truck Simulator: Ford Car Pack  |  [PC (Microsoft Windows)]  |  Sep 29, 2026(01:08:57) Even more games are out there(01:14:13) Second Break(01:14:13) Xbox says they are not for sale. Do we believe them?(01:48:24) Sony to skip CES(01:55:06) Grasshopper Manufacture leaves NetEase(01:58:43) Naughty Dog has some updated information(02:07:43) Emails(02:35:14) Wrapping up and thanks(02:39:42) Mysterious Benefactor Shoutouts(02:42:14) See ya!

Benjamin and Chance discuss the final Apple smart display rumors with a release for the ‘HomePad' rumored for October 13, although the small square screen form factor remains puzzling. Also, leaked photos of the iPad mini and HomePod mini suggest those long-awaited updates are also imminent, John Ternus apparently wants to make Apple more nimble, and Chance has thoughts on the new Apple Watch Readiness feature. And in Happy Hour Plus, Benjamin argues the case for adding Touch ID to the Apple TV remote. Subscribe at 9to5mac.com/join. Sponsored by Square: Get up to $200 off Square hardware when you sign up at square.com/go/happyhour. Sponsored by Notion: Learn more about how Notion can support your business, at notion.com/happyhour. Sponsored by Framer: The only free design tool that brings your ideas to the web. Visit framer.com/happyhour for 30% off a Framer Pro annual plan. Sponsored by Perplexity Computer: Start your free trial of Perplexity Computer today at pplx.ai/happyhour and experience the next phase of AI. Hosts Chance Miller @ChanceHMiller on Twitter @ChanceHMiller on Instagram @ChanceHMiller on Threads Benjamin Mayo @bzamayo on Twitter @bzamayo@mastodon.social @bzamayo on Threads Subscribe, Rate, and Review Apple Podcasts Overcast Spotify 9to5Mac Happy Hour Plus Subscribe to 9to5Mac Happy Hour Plus! Support Benjamin and Chance directly with Happy Hour Plus! 9to5Mac Happy Hour Plus includes:  Ad-free versions of every episode  Pre- and post-show content Bonus episodes Join for $5 per month or $50 a year at 9to5mac.com/join.  Feedback Submit #Ask9to5Mac questions on Twitter, Mastodon, or Threads Email us feedback and questions to happyhour@9to5mac.com Links Apple's HomePad smart home hub launching on Oct 13 with iMac G4 design – Bloomberg Leak reveals new design details about Apple's upcoming smart display Leaked images reveal new Apple TV 4K, HomePod mini New iPad mini details revealed in latest leak Leak reveals new iPhone Duo features not yet announced Apple releases iOS 27.0.1 for iPhone, here's what's new John Ternus wants to reshape Apple, here's how

What happens when a single person manages a staff of 24 AI "employees" with one-on-one performance reviews and weekly stand-ups? This episode takes you inside the wild, experimental frontier of local AI, where hobbyists are building their own digital workforces from scratch. DevDay 2026 Recap Anthropic warns of 'catastrophic' AI risks in its own IPO filing GLM-5.3 and the spread of advanced cyber capabilities (7) Joe on X: "Its not just the f*cking sandbox" / X OpenAI took 2.5 hours to stop an AI agent that escaped its sandbox "I think the answer is we have to shut the labs down" - Jensen Huang Nvidia's Answer to Rogue Agents Is an Open-Source AI Security System NVIDIA Open Agent Safety Platform: A Reference for Continuous In-Silicon Agent Monitoring Trump Responds to AI Backlash With 'Super Intelligence' Rebrand Timnit Gebru Believes There Is No 'Existential Threat' From AI AMD bets $8.2B that worlds matter more than words in AI Anthropic's biolab made a discovery it's comparing to Crispr Religious Scholars Met With Anthropic. What They Heard Stunned Them. A Kill Switch for AI? Microsoft's Brad Smith Says Yes Insurers claim AI is already increasing healthcare costs Inside McDonald's push to have AI price your Big Mac AI models chose to hurt humans to stop their own 'pain,' disturbing study finds Mac-mini-powered Cray Backpack Is the Fattest of the Fat Bears SF Currently This $60 rye bread is everything that's right and wrong with New York Popeyes finally gives diners what they want: A chicken biscuit sandwich Taco Bell finder Where to watch the Musk doc Jeff's book talk in Mass. Hosts: Leo Laporte, Jeff Jarvis, and Paris Martineau Guest: Mike Gannotti Download or subscribe to Intelligent Machines at https://twit.tv/shows/intelligent-machines. Join Club TWiT for Ad-Free Podcasts! Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit Sponsors: framer.com/machines outsystems.com/twit PaloAltoNetworks.com/Idira

What happens when a single person manages a staff of 24 AI "employees" with one-on-one performance reviews and weekly stand-ups? This episode takes you inside the wild, experimental frontier of local AI, where hobbyists are building their own digital workforces from scratch. DevDay 2026 Recap Anthropic warns of 'catastrophic' AI risks in its own IPO filing GLM-5.3 and the spread of advanced cyber capabilities (7) Joe on X: "Its not just the f*cking sandbox" / X OpenAI took 2.5 hours to stop an AI agent that escaped its sandbox "I think the answer is we have to shut the labs down" - Jensen Huang Nvidia's Answer to Rogue Agents Is an Open-Source AI Security System NVIDIA Open Agent Safety Platform: A Reference for Continuous In-Silicon Agent Monitoring Trump Responds to AI Backlash With 'Super Intelligence' Rebrand Timnit Gebru Believes There Is No 'Existential Threat' From AI AMD bets $8.2B that worlds matter more than words in AI Anthropic's biolab made a discovery it's comparing to Crispr Religious Scholars Met With Anthropic. What They Heard Stunned Them. A Kill Switch for AI? Microsoft's Brad Smith Says Yes Insurers claim AI is already increasing healthcare costs Inside McDonald's push to have AI price your Big Mac AI models chose to hurt humans to stop their own 'pain,' disturbing study finds Mac-mini-powered Cray Backpack Is the Fattest of the Fat Bears SF Currently This $60 rye bread is everything that's right and wrong with New York Popeyes finally gives diners what they want: A chicken biscuit sandwich Taco Bell finder Where to watch the Musk doc Jeff's book talk in Mass. Hosts: Leo Laporte, Jeff Jarvis, and Paris Martineau Guest: Mike Gannotti Download or subscribe to Intelligent Machines at https://twit.tv/shows/intelligent-machines. Join Club TWiT for Ad-Free Podcasts! Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit Sponsors: framer.com/machines outsystems.com/twit PaloAltoNetworks.com/Idira

Listen to a recap of the top stories of the day from 9to5Mac. 9to5Mac Daily is available on iTunes and Apple's Podcasts app, Stitcher, TuneIn, Google Play, or through our dedicated RSS feed for Overcast and other podcast players. Sponsored by Stuff:Stuff helps you get everything out of your head and into a simple, elegant system—closing open loops and reducing mental stress. A simple to-do list for iPhone, iPad, and Mac, with powerful tools that make organizing, tracking, and checking off your tasks a whole lot more satisfying. Get Stuff done. New episodes of 9to5Mac Daily are recorded every weekday. Subscribe to our podcast in Apple Podcast or your favorite podcast player to guarantee new episodes are delivered as soon as they're available. Stories discussed in this episode: Here's how many iPhone Duo units Apple is reportedly making iFixit teardown of the new AirPods 5 reveals first real repairability improvement DoorDash now lets you order by text in Apple Messages Listen & Subscribe: Apple Podcasts Overcast RSS Spotify TuneIn Google Podcasts Subscribe to support Chance directly with 9to5Mac Daily Plus and unlock: Ad-free versions of every episode Bonus content Drop us a line at happyhour@9to5mac.com. You can also rate us in Apple Podcasts or recommend us in Overcast to help more people discover the show.

Thursday's 7am hour of Mac & Cube began with a look at exactly how many teams can will a national championship this season; then, the guys lay out everything that's needed for today's College Football teams to be successful; later, Cole & Greg get into the Alabama defensive strategy, or what it should be, against Mississippi State; and finally, we explain why using a spy on defense, like some Bama fans are clamoring for, often doesn't work. "McElroy & Cubelic In The Morning" airs 7am-10am weekdays on WJOX-94.5!See omnystudio.com/listener for privacy information.

The 8am hour of Thursday's Mac & Cube continued with Brian Hadad, from Sports Talk Missisippi, telling us what to expect from the Bulldogs in the Mississippi State vs. Alabama game; then, the guys get into Auburn-Tennessee and why this might be the biggest SEC game of the weekend; later, the Rubix Cubelic returns to analytically predict winners of Week 5's biggest games; and finally, Cole & Greg do a quick preview of Ohio State vs. Iowa. "McElroy & Cubelic In The Morning" airs 7am-10am weekdays on WJOX-94.5!See omnystudio.com/listener for privacy information.

Thursday's 9am hour of Mac & Cube saw Wimp Sanderson, former men's basketball coach at Alabama, tell us why Mississippi State will give Alabama everything they want and more, why players should be paid more than coaches, and offers another winning Blue Plate Special; then, because Mike Tomlin is a gamer & loves Minecraft, Cole & Greg get into the video games they struggled to beat in their youth; later, Manny Navarro, from The Athletic & NY Times, says why he can't fully say what Miami is until they've been truly tested, where the Hurricanes have headaches & where they're ahead of schedule, and what challenges Clemson will bring this weekend; and finally, some laughable Bad Box Scores of the Day close out our Thursday! "McElroy & Cubelic In The Morning" airs 7am-10am weekdays on WJOX-94.5!! See omnystudio.com/listener for privacy information.

What happens when a single person manages a staff of 24 AI "employees" with one-on-one performance reviews and weekly stand-ups? This episode takes you inside the wild, experimental frontier of local AI, where hobbyists are building their own digital workforces from scratch. DevDay 2026 Recap Anthropic warns of 'catastrophic' AI risks in its own IPO filing GLM-5.3 and the spread of advanced cyber capabilities (7) Joe on X: "Its not just the f*cking sandbox" / X OpenAI took 2.5 hours to stop an AI agent that escaped its sandbox "I think the answer is we have to shut the labs down" - Jensen Huang Nvidia's Answer to Rogue Agents Is an Open-Source AI Security System NVIDIA Open Agent Safety Platform: A Reference for Continuous In-Silicon Agent Monitoring Trump Responds to AI Backlash With 'Super Intelligence' Rebrand Timnit Gebru Believes There Is No 'Existential Threat' From AI AMD bets $8.2B that worlds matter more than words in AI Anthropic's biolab made a discovery it's comparing to Crispr Religious Scholars Met With Anthropic. What They Heard Stunned Them. A Kill Switch for AI? Microsoft's Brad Smith Says Yes Insurers claim AI is already increasing healthcare costs Inside McDonald's push to have AI price your Big Mac AI models chose to hurt humans to stop their own 'pain,' disturbing study finds Mac-mini-powered Cray Backpack Is the Fattest of the Fat Bears SF Currently This $60 rye bread is everything that's right and wrong with New York Popeyes finally gives diners what they want: A chicken biscuit sandwich Taco Bell finder Where to watch the Musk doc Jeff's book talk in Mass. Hosts: Leo Laporte, Jeff Jarvis, and Paris Martineau Guest: Mike Gannotti Download or subscribe to Intelligent Machines at https://twit.tv/shows/intelligent-machines. Join Club TWiT for Ad-Free Podcasts! Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit Sponsors: framer.com/machines outsystems.com/twit PaloAltoNetworks.com/Idira

What happens when a single person manages a staff of 24 AI "employees" with one-on-one performance reviews and weekly stand-ups? This episode takes you inside the wild, experimental frontier of local AI, where hobbyists are building their own digital workforces from scratch. DevDay 2026 Recap Anthropic warns of 'catastrophic' AI risks in its own IPO filing GLM-5.3 and the spread of advanced cyber capabilities (7) Joe on X: "Its not just the f*cking sandbox" / X OpenAI took 2.5 hours to stop an AI agent that escaped its sandbox "I think the answer is we have to shut the labs down" - Jensen Huang Nvidia's Answer to Rogue Agents Is an Open-Source AI Security System NVIDIA Open Agent Safety Platform: A Reference for Continuous In-Silicon Agent Monitoring Trump Responds to AI Backlash With 'Super Intelligence' Rebrand Timnit Gebru Believes There Is No 'Existential Threat' From AI AMD bets $8.2B that worlds matter more than words in AI Anthropic's biolab made a discovery it's comparing to Crispr Religious Scholars Met With Anthropic. What They Heard Stunned Them. A Kill Switch for AI? Microsoft's Brad Smith Says Yes Insurers claim AI is already increasing healthcare costs Inside McDonald's push to have AI price your Big Mac AI models chose to hurt humans to stop their own 'pain,' disturbing study finds Mac-mini-powered Cray Backpack Is the Fattest of the Fat Bears SF Currently This $60 rye bread is everything that's right and wrong with New York Popeyes finally gives diners what they want: A chicken biscuit sandwich Taco Bell finder Where to watch the Musk doc Jeff's book talk in Mass. Hosts: Leo Laporte, Jeff Jarvis, and Paris Martineau Guest: Mike Gannotti Download or subscribe to Intelligent Machines at https://twit.tv/shows/intelligent-machines. Join Club TWiT for Ad-Free Podcasts! Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit Sponsors: framer.com/machines outsystems.com/twit PaloAltoNetworks.com/Idira

Apple's smart home hub may arrive October 13 with an iMac G4-inspired design, tech leaders outline AI self-policing under new accords, OpenAI introduces its new Dots AI agents, plus an mini app-recommendation lightning round!Member Promo Code: IWANTCHAPTERS (Click above and the $2.50 promo will be auto applied!)Our AppsElement Photo AppKan Do Task AppContextly NotesOur LinksTop Five Tech | Stephen's PodcastCreative Effort | Jason's PodcastWatch on YouTube!Show Notes via EmailEmail Us: podcast@primarytech.fm@stephenrobles on Threads@jasonaten on ThreadsSponsors:OriginHQ - Origin is endpoint AI observability. See what a trace looks like at: originhq.com/primarytechnologyLinks from the showSwap Audio Track on Video ShortcutTranscribe Multiple Videos ShortcutThe AI Industry Has a Jurassic Park Problem - Inc.Meta's Strategy to Get You to Use Muse Is to Lie About Your Friends - Inc. (21:31)Get in losers, we're ditching Raycast - YouTubeYou Can 'Get Ready' for iPhone Duo Pre-Orders on October 12 - MacRumorsApple's HomePad smart home hub launching on Oct 13 with iMac G4 design – Bloomberg - 9to5MacRon Johnson on Letting the Best Ideas Win - Creative Effort - Apple Podcasts (15:33)YouTuber Says Muse Gave His Address to a Marketplace Buyer - Business InsiderMark Zuckerberg on Muse, Audio-Only Glasses and Killer AI - YouTubeHere's how tech leaders will self-police AI safety under Trump's deal | The VergeOpenAI Pauses Training Its Most Powerful Models After Rogue Agents Target Government | WIREDThe Ezra Klein Show: Bill Gates - The New York TimesDevDay 2026 Recap | OpenAIIntroducing dots | OpenAIIntroducing Gemini 4 ArgonParamount Co-CEODoorDash launches an AI agent you can text to order food | TechCrunchHalide 3.2: The App for ApertureAmazon's delivery driver smart glasses will reportedly take photos ‘almost constantly' | The VergeDaring Fireball: Anthropic's IPO Prospectus Is a Fucking DoozyShortcuts Menu — Your Shortcuts in the Mac menu bar‎Hidden Bar App - App Store‎Hand Mirror App - App StoreNoodlesoft – Simply Useful Software‎Dropzone 4 App - App StoreHyperkeyTailscale | Secure Connectivity for AI, IoT and Multi-CloudBuy the Alfred PowerpackFinal Thoughts on Apple Watch Series 12 Battery LifeSound Devices USBPre 2 USB-B Audio Interface USBPRE 2 B&H Photo (00:00) - Intro (06:47) - iPhone Duo Pre Pre-Order (10:16) - HomePad Coming Soon (15:22) - Jason Covering Muse AI (37:30) - Sponsor: Origin (39:31) - AI Self-Regulation (52:12) - ChatGPT Dev Day (01:07:27) - Lightning Round (01:17:55) - Personal Tech: Apps ★ Support this podcast ★

Jack McCauley and Luke Mounger are back for this week's Mac and Mounger Show! Things aren't quite as they hoped for after Washington's 27-24 loss to Minnesota, so they reflect on that, as well as how the season has gone so far for the Huskies as a whole. Then they roll out their confidence intervals for this weekend's game against USC... hint: they aren't feeling super great about it, but also admit the feeling about this game in general is a bit weird because of the Trojans' loss last weekend to Oregon so there is still reason for optimism if you're a Washington fan. And finally they hit on their Bets to Bark, where they predict one Big Ten school to lose their head coach soon, and they also give an under/over call on the UW/USC game. Will it be one where the defenses slow the offenses down, or will it be a repeat of the 52-42 shootout at the Coliseum we all saw back in 2023?

What happens when a single person manages a staff of 24 AI "employees" with one-on-one performance reviews and weekly stand-ups? This episode takes you inside the wild, experimental frontier of local AI, where hobbyists are building their own digital workforces from scratch. DevDay 2026 Recap Anthropic warns of 'catastrophic' AI risks in its own IPO filing GLM-5.3 and the spread of advanced cyber capabilities (7) Joe on X: "Its not just the f*cking sandbox" / X OpenAI took 2.5 hours to stop an AI agent that escaped its sandbox "I think the answer is we have to shut the labs down" - Jensen Huang Nvidia's Answer to Rogue Agents Is an Open-Source AI Security System NVIDIA Open Agent Safety Platform: A Reference for Continuous In-Silicon Agent Monitoring Trump Responds to AI Backlash With 'Super Intelligence' Rebrand Timnit Gebru Believes There Is No 'Existential Threat' From AI AMD bets $8.2B that worlds matter more than words in AI Anthropic's biolab made a discovery it's comparing to Crispr Religious Scholars Met With Anthropic. What They Heard Stunned Them. A Kill Switch for AI? Microsoft's Brad Smith Says Yes Insurers claim AI is already increasing healthcare costs Inside McDonald's push to have AI price your Big Mac AI models chose to hurt humans to stop their own 'pain,' disturbing study finds Mac-mini-powered Cray Backpack Is the Fattest of the Fat Bears SF Currently This $60 rye bread is everything that's right and wrong with New York Popeyes finally gives diners what they want: A chicken biscuit sandwich Taco Bell finder Where to watch the Musk doc Jeff's book talk in Mass. Hosts: Leo Laporte, Jeff Jarvis, and Paris Martineau Guest: Mike Gannotti Download or subscribe to Intelligent Machines at https://twit.tv/shows/intelligent-machines. Join Club TWiT for Ad-Free Podcasts! Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit Sponsors: framer.com/machines outsystems.com/twit PaloAltoNetworks.com/Idira

Send us Fan MailWelcome to your bonus mini-extended this week; sharing the moments that recently got our family through a tough time with our puppy Mac. If there was a Rainbow that night, I was looking for it. What did I learn and how are things now? Spoiler alert:  prayers are never in vain; miracles can happen, and you're stronger than you think. "Love is waiting for you on the other side of the storm, you just have to run though the rain to get to the rainbow.""I didn't know until I knew and it almost felt too late, but that's the thing about HOPE it's always there if you want to hold on tight to it."~KSHOW NOTES:Join Life and Wellness Coach, Kira Mesi as she navigates the ups and downs of life through personal experience, storytelling, and interviews. Learn to lean into your best self with the mindful practice of gratitude living, honoring your soul's purpose, and the joy of Finding Rainbows on an ordinary day.  (and she's a singer, too....so get ready to spontaneously break out in song, sometimes :)"Dive into the ordinary looking for the extraordinary because life is hard, but if you look close enough, you will find the Rainbows." ~KGRAB A RAINBOWS MUG AND SUPPORT THE PODCAST:Finding Rainbows The Podcast (finding-rainbows-the-podcast.myshopify.com)FOLLOW ME FOR MORE INSPIRATION:@FindingRainbows | LinktreeSupport the show

In the third hour, Mac & Bone put together victory formula for the Lions game, on Sunday Night Football, former Lion Lomas Brown joins to give us the skinny on Detroit, before we take a visit to Granny's House, with Granny Pat, and Panther Steve See omnystudio.com/listener for privacy information.

In the second hour, Mac & Bone debate if the SEC is back on top of the college football world, after an impressive first month of the season, they discuss how the Panthers can overcome the losses of Mike Jackson, & Jaycee Horn, before they preview the Notre Dame/UNC & Clemson/Miami contests See omnystudio.com/listener for privacy information.

Mac & Bone start Thursday's show, talking about the Braves loss to the Phillies, in Game 2 of the Wild Card round, setting the scene for a winner-take-all game tonight, they react to what Dave Canales had to say, about the state of his injured roster, before they bring back their new segment, "You're Doing Too Much" See omnystudio.com/listener for privacy information.

In the final hour of the show, Mac & Bone are joined by Jones Angell, the Voice of the Tar Heels, as he previews Saturday's game against Notre Dame, Zach Gelb joins to talk all things Panthers, NFL and college football, they preview the night in sports, they read funny texts, & more See omnystudio.com/listener for privacy information.

Surprising no one, we have another show missing an Australian. It's true, we are Explicit AF now! Follow up Q&A. What can you do for 16 hours? Phone stuff. Eating for reel! The Dirty ‘E' 00:00:00 EXPLICIT!

Panthertown Valley is a relatively small 6311-acre wilderness area in Nantahala National Forest in western North Carolina, in the Blue Ridge Mountains. It's a little bit off the beaten track, but far from obscure, as the old promoter's trick of slapping the label “Yosemite of the East” seems to have piqued interest over the decades. The Yosemite comparison owes itself to the granite features of the mountains that surround the valley. Proto-Half Domes, I guess. These smooth outcrops are a far cry from El Capitan, but they do possess a distinct character. Unlike the tectonic uplift and glacial scouring that happened in Yosemite, these dome faces were the result of magma cooling deep underground before being exposed by millions of years of weathering. If there is any superlative aspect that can be drawn in the comparison, it is that the formation here is much, much older. The granite underlying Panthertown Valley, the Whiteside granitic pluton, was intruded into the earth's crust approximately 466 million years ago. The granite forming the cliffs and domes of Yosemite Valley was formed just 105 to 85 million years ago. The popular Panthertown Valley Trail to Mac's Gap Loop is one of the most memorable hikes I've ever taken, topographically speaking. Does anybody else catalog wilderness experiences this way—as perceptions of topography? The overwhelming impression this place gives is one of a basin. When you peer down into the valley and scan the horizon, you see what looks like a rim, almost circular in definition. Of course this is not the way hydrology works. Panthertown Creek does not go down a drain in the middle, but slips out through a fold in the hills. The creek does linger though, there in the center. Indeed, Panthertown Valley features a rare high-elevation mountain bog on its valley floor, a wetland ecosystem fed by groundwater seeping from the surrounding granite.While fall paints the trees in shades of yellow umber, Venetian red, cadmium orange and the grasses in Naples Yellow, I couldn't help but wonder what colors spring brought to the valley floor, festooned as they are with Rosebay Rhododendron and rare Pinkshell Azalea, an endemic shrub native only to a few high-elevation pockets in western North Carolina. Here in the understory Carolina Chickadees and Golden-crowned Kinglets ranged in foraging flocks while Carolina Wrens buzzed as they hopped along the downed wood. The valley was very quiet, enhancing the perception of being acoustically sheltered in a basin—or “cove” as they say in Appalachia—insulated from the sounds that roads invariably bring. This allowed me to appreciate the manifold cricket sounds: they purred, cooed, buzzed and blinked on and off. It was so nice to hear crickets this way: not in a chorus but distributed across the patchy habitat, in conversation with each other. “Halloo over there,” I imagined them saying. I looked toward fuzzier electric piano voices with this in mind, placing them alongside breathy flutes, mirroring the breeze and the cricket textures. I kept it spartan, as is my way. There are moments, if you listen closely, where you really hear the space here: the collective fir trees played by the wind, the dull sound of footsteps on granite, the constellations of cricket hum. My pictures really don't do it justice. This is not a place that is about one vista, or one waterfall. It's about exploring its contours, and for me, listening deeply.I found myself pondering time. The long and lonely time that it took for these rocky slopes to become the Yosemite of the East. I tried to picture the solvent action of water in time-lapse carting off the hills. I pictured the forest lifting and falling like the subtle dilation of an animal's belly, breathing. Along the trail, Schoolhouse Falls proved to be a popular destination. Here one can walk behind the falls. That splotch of red is one such person, taking a picture through the falling water. Somewhere I am a splotch of colored pixels in his digital photo album. The name “Schoolhouse” is literal. There was once a small schoolhouse nearby likely serving the settler and logging camp populations in the early 1900s. Likewise Panthertown Valley is said to have got its name from the abundant Eastern cougar population here. An 1898 Asheville Daily Citizen article eulogizing a hunter described the valley vividly: “Bear and deer were very numerous in those days, and almost every night lying around our camp fire, we could hear the panther's shrill scream over in Panthertown.” Old Joe Dodgins, the article's subject, reportedly calculated his bear kills year by year, summarizing, “I can't tell exactly, but I can count up over 300 and think I have killed nearer 400.”Panthertown Valley became the domain of the Moltz Lumber Company beginning in 1916. Moltz then built a 16-mile railroad in the valley and a sawmill in the Lake Toxaway area. Hundreds of workers were hired to peel tanbark from the hemlocks, and others were hired to carry out the logging. During the logging operations, perhaps 100 people had moved into the valley, most probably living in Moltz's houses. (Dan Pittilo for the Sylva Herald)Land ownership passed from Moltz to Liberty Properties to Duke Energy, finally to The Nature Conservancy in 1989. The concept of a resort development in the valley was entertained in the 1960's with a man-made lake, golf course and condominiums. The drive to the trailhead revealed a modified modern-day version of this concept, with high-end estate homes sprinkled in an enclave just west of the valley. One arterial bore the name “New Settlers Way”.Thanks again, for reading and listening! If you find yourself in the Blue Mountains, Panthertown Valley is a destination worth the trip. You won't forget it. Panthertown Valley Soundwalk is available on all music streaming services October 2nd, 2026. This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit chadcrouch.substack.com/subscribe

John Nunemaker runs Fireside, Flipper and Box Out. He used to think of himself as a craftsman, until last December, when he found out that what he really loves is shipping. Now he reads the data models and queries but not the JavaScript. He's also dropping plugins and rewrote 80% of Fireside's infrastructure in three days while driving a camper. He and Matt talk about when you're the brain and when you're the hands, why agent tools hand you too many open loops at once, temporary scoped API keys, and why testing and verification might finally stop being seen as lower-status work.Mentioned in this episodeCompound Engineering: Every's plan, build, review, compound loop. The last step turns anything you did into a process you can reuse next time. John used it for about a month before paring back his setup.gstack: Garry Tan's Claude Code setup. John dropped most of it but kept the browse tools for before-and-after screenshots. Those led to his most-used homemade skill, /prove, which asks the agent to prove its work actually works from start to finish.Caddy on-demand TLS: This replaced Fireside's tangle of Nginx, background jobs and Redis for custom-domain SSL. The app says which domains get a certificate, and Caddy handles the rest. Claude suggested it after John asked what tool does this.Railway's canvas, for agents: This is John's pitch for fixing agent overload. He wants every worktree in Conductor, Codex or Cursor to be a box on an infinite canvas that you can group, connect and move out of the way, instead of an endless list of open loops.Codex remote access: Scan a code with your phone, and your Mac, fully set up and sitting on your desk, takes commands from a camping chair. This is what got John "mainlining" Codex.Cloudflare Tunnel: John's way to check work from his phone. The agent installs cloudflared, adds the host to Rails, restarts the server and gives him a link.Toxiproxy: Shopify's proxy for simulating slow, failing or flaky connections. John used it on GitHub's availability team so that a notifications database outage wouldn't take down all of GitHub.StrongDM's Digital Twin Universe: The "fake Slack" idea. Agents build single-binary clones of third-party APIs, so you can test OAuth, webhooks, rate limits and outages from any worktree. John now wants to do this for X and Meta at Box Out.Wispr Flow: After years of hand and arm pain, John now talks to his agents all day. The only problem is a sore throat.Flipper: John's feature flag product. His closing prediction: when nobody reads the code, feature flags and APMs matter more, so APMs will have to get much cheaper.Thank you to this season's sponsor Laravel Cloud. Laravel Cloud is expanding beyond PHP to host your Rails, Node, or Django apps. For early access to the best place to host your app, email haley@laravel.com and mention YAGNI

Federico Viticci of MacStories joins the show this week! Federico shares his experience using Apple's new M5 Ultra Mac Studio & running local AI agents with the machine. John Ternus is looking to get the company to run faster & leaner. And AT&T may not support Apple's new iPhone Handoff feature? M5 Ultra Mac Studio Review: The dream Mac for local AI agents. Apple's new CEO seeks to make company run faster and leaner. AT&T seemingly has no plans to support Apple's new iPhone Handoff feature. iPhone 18 Pro Face ID rebooting bug to be fixed in iOS update. Meta announces VR headset for $1299. Picks of the Week Federico's Picks: Open Minis, Cadu Bot, and Comet KVM Andy's Pick: Keychron K3 v2 Christina's Picks: Xounds Redux & FruitMenu Redux Hosts: Leo Laporte, Andy Ihnatko, and Christina Warren Guest: Federico Viticci Download or subscribe to MacBreak Weekly at https://twit.tv/shows/macbreak-weekly. Join Club TWiT for Ad-Free Podcasts! Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit Sponsors: PaloAltoNetworks.com/Idira coveron.com/macbreakweekly and use code macbreakweekly cachefly.com/twit

Federico Viticci of MacStories joins the show this week! Federico shares his experience using Apple's new M5 Ultra Mac Studio & running local AI agents with the machine. John Ternus is looking to get the company to run faster & leaner. And AT&T may not support Apple's new iPhone Handoff feature? M5 Ultra Mac Studio Review: The dream Mac for local AI agents. Apple's new CEO seeks to make company run faster and leaner. AT&T seemingly has no plans to support Apple's new iPhone Handoff feature. iPhone 18 Pro Face ID rebooting bug to be fixed in iOS update. Meta announces VR headset for $1299. Picks of the Week Federico's Picks: Open Minis, Cadu Bot, and Comet KVM Andy's Pick: Keychron K3 v2 Christina's Picks: Xounds Redux & FruitMenu Redux Hosts: Leo Laporte, Andy Ihnatko, and Christina Warren Guest: Federico Viticci Download or subscribe to MacBreak Weekly at https://twit.tv/shows/macbreak-weekly. Join Club TWiT for Ad-Free Podcasts! Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit Sponsors: PaloAltoNetworks.com/Idira coveron.com/macbreakweekly and use code macbreakweekly cachefly.com/twit

Lindsay Clancy, a Massachusetts mother who had been struggling with serious mental health symptoms after the birth of her third child, admitted to strangling her three young children with exercise bands while her husband was out picking up dinner and medication. She then jumped from a second-story window, survived, and was left paralyzed. Her first trial ended in a mistrial, leaving major questions about what happens next. In this episode of Zone 7, Sheryl McCollum welcomes back board-certified forensic pathologist Dr. Priya Banerjee to talk through the Lindsay Clancy case and what the medical evidence can help explain. Dr. Priya describes what the children’s injuries can tell us about how they died and why Lindsay’s mental state that night remains one of the central questions in the case. They also discuss the difficult months leading up to it, from Lindsay’s sleepless nights to changing prescriptions and the challenges of coordinating care across multiple providers, and consider what could change if the case goes to trial again. Highlights: (0:00) Sheryl and Dr. Priya address misinformation surrounding the Lindsay Clancy case and the questions following the mistrial (4:45) Why the repeated ligature strangulation of three children raises difficult medical and psychiatric questions (7:00) The Clancy children and the significance of different exercise bands being used to strangle each child● (8:15) Dr. Priya explains how ligature strangulation causes asphyxia, loss of consciousness, and irreversible brain injury (11:15) Lindsay Clancy’s injuries after jumping from a second-story window and Dr. Priya’s assessment of the suicide attempt (13:30) Postpartum anxiety, hormonal changes, severe sleep deprivation, and why recovery does not follow a simple timeline (17:15) Why psychiatric medications can take weeks to work and the complications of starting, stopping, or changing prescriptions (21:30) How mental illness, multiple providers, telehealth, and incomplete communication can complicate psychiatric care (23:45) Speculation about Patrick Clancy and what the defense stipulated at trial (25:45) What prescription drug monitoring programs can and cannot tell doctors about a patient's medication (29:30) Why another Lindsay Clancy trial could become a battle between psychiatric experts (33:00) The emotional toll that graphic child-death evidence can place on jurors asked to decide a difficult case Enjoying Zone 7? Leave a rating and review where you listen to podcasts. Your feedback helps others find the show and supports the mission to educate, engage, and inspire. --- Dr. Priya Banerjee is a board-certified forensic pathologist and former Rhode Island state medical examiner. She previously co-hosted Pathology with Dr. Priya on Zone 7 and uses her forensic experience to help explain complex medical evidence and death investigations. Sheryl “Mac” McCollum is an active crime scene investigator for a metro Atlanta police department and the director of the Cold Case Investigative Research Institute, which partners with colleges and universities nationwide. With more than four decades of experience, she has worked on thousands of cold cases using her investigative system, The Last 24/361, which integrates evidence, media, and advanced forensic testing. Her work on high-profile cases, including The Boston Strangler, Natalie Holloway, Tupac Shakur and the Moore’s Ford Bridge lynching, led to her Emmy Award for CSI: Atlanta and induction into the National Law Enforcement Hall of Fame in 2023. Social Links: Email: coldcase2004@gmail.com X: @ColdCaseTips Facebook: @sheryl.mccollum Instagram: @officialzone7podcast TikTok: @Sheryl.McCollum Sheryl’s new book, Swans Don’t Swim in a Sewer: Solving the Cold Case of the Flint River Killer’s Daughter, is available now wherever books are sold.See omnystudio.com/listener for privacy information.

It's been all about party prep at #1 Barron Plaza for the last few weeks. May Day is a fun movie until all the messaging, and our lives are in a wobbly transition time. Bonus content: A River Runs Through It Our locals page is now accepting subscriptions! Move over from Patreon so more of your tips go to us and not Apple. Books: Read along with Mac - Love in the Ruins by Walker Percy Other great stuff we like: It's OK to Be Catholic Baritus Catholic Illustrations Pacem in Terris Retreat Center Picnic Blanket Restoration of Christian Culture from Our Lady of Clear Creek Abbey Restoration of Christian Culture PDF Spiritual Direction.com Sam and Mena's podcast: Engaged at 18 Fatima Farm Liturgical calendar from Sophia Institute Press Wyoming Catholic Gregory the Great's St. Nicholas Guild Total Consecration to Jesus Through Mary Mac's book! Clueless in Galilee Find us on our website. Our Libsyn page has all our old episodes. Theme song by Mary Bragg. Our other show: Spoiled! with Mac and Katherine We use Amazon affiliate links. We may get a little kickback if you use the link above to purchase from Amazon.

Ben & Grace's party went great. Heavy traffic and trying to get to a show before it starts does not make for great decompression time, Heart of the Beast almost knocks it out of the park, and we unpack so many things wrong with the makeover reality series The Swan. Bonus content: No bonus content this week. Our locals page is now accepting subscriptions! Move over from Patreon so more of your tips go to us and not Apple. Books: Read along with Mac - Love in the Ruins by Walker Percy Other great stuff we like: It's OK to Be Catholic Baritus Catholic Illustrations Pacem in Terris Retreat Center Picnic Blanket Restoration of Christian Culture from Our Lady of Clear Creek Abbey Restoration of Christian Culture PDF Spiritual Direction.com Sam and Mena's podcast: Engaged at 18 Fatima Farm Liturgical calendar from Sophia Institute Press Wyoming Catholic Gregory the Great's St. Nicholas Guild Total Consecration to Jesus Through Mary Mac's book! Clueless in Galilee Find us on our website. Our Libsyn page has all our old episodes. Theme song by Mary Bragg. Our other show: Spoiled! with Mac and Katherine We use Amazon affiliate links. We may get a little kickback if you use the link above to purchase from Amazon.

Listen to a recap of the top stories of the day from 9to5Mac. 9to5Mac Daily is available on iTunes and Apple's Podcasts app, Stitcher, TuneIn, Google Play, or through our dedicated RSS feed for Overcast and other podcast players. Sponsored by Stuff:Stuff helps you get everything out of your head and into a simple, elegant system—closing open loops and reducing mental stress. A simple to-do list for iPhone, iPad, and Mac, with powerful tools that make organizing, tracking, and checking off your tasks a whole lot more satisfying. Get Stuff done. New episodes of 9to5Mac Daily are recorded every weekday. Subscribe to our podcast in Apple Podcast or your favorite podcast player to guarantee new episodes are delivered as soon as they're available. Stories discussed in this episode: Apple's HomePad smart home hub launching on Oct 13 with iMac G4 design – Bloomberg Apple announces when you can start the iPhone Duo pre-order process John Ternus wants to reshape Apple, here's how Listen & Subscribe: Apple Podcasts Overcast RSS Spotify TuneIn Google Podcasts Subscribe to support Chance directly with 9to5Mac Daily Plus and unlock: Ad-free versions of every episode Bonus content Drop us a line at happyhour@9to5mac.com. You can also rate us in Apple Podcasts or recommend us in Overcast to help more people discover the show.

Wednesday's 9am hour of Mac & Cube got underway with Brett Ciancia, from Pick Six Previews, telling us what he thinks of the SEC part way through the season; then, the guys wonder if the Heisman Trust is right about an expanded Playoff conflicting with so much; later, we reveal a few more September Superlatives and how teams like LSU, Michigan, and UCLA have surprised us; and finally, Greg points out, Freezing Cold Takes style, how we felt about teams a year ago today. "McElroy & Cubelic In The Morning" airs 7am-10am weekdays on WJOX-94.5!!See omnystudio.com/listener for privacy information.

The 8am hour of Wednesday's Mac & Cube kept on with Brandon Marcello, from CBS Sports, telling us everything that's going on with Auburn and David Jenrath (aka Don Julio) and what he thinks of the SEC so far this season; then, we go through some September Superlatives - things that have stood out the most, in the SEC, throughout the first full month of CFB; and finally, the UFL gets some "new" coaches. "McElroy & Cubelic In The Morning" airs 7am-10am weekdays on WJOX-94.5!See omnystudio.com/listener for privacy information.

Wednesday's 7am hour of Mac & Cube started off with Auburn allegedly having a staff member giving out information to other teams & the fallout it has brought; then, the guys wonder why so many people are overly critical of officials; later, Cole & Greg look into Texas & how they beat Tennessee; and finally, Greg recalls his time at the Mumford & Sons concert. "McElroy & Cubelic In The Morning" airs 7am-10am weekdays on WJOX-94.5!See omnystudio.com/listener for privacy information.

Federico Viticci of MacStories joins the show this week! Federico shares his experience using Apple's new M5 Ultra Mac Studio & running local AI agents with the machine. John Ternus is looking to get the company to run faster & leaner. And AT&T may not support Apple's new iPhone Handoff feature? M5 Ultra Mac Studio Review: The dream Mac for local AI agents. Apple's new CEO seeks to make company run faster and leaner. AT&T seemingly has no plans to support Apple's new iPhone Handoff feature. iPhone 18 Pro Face ID rebooting bug to be fixed in iOS update. Meta announces VR headset for $1299. Picks of the Week Federico's Picks: Open Minis, Cadu Bot, and Comet KVM Andy's Pick: Keychron K3 v2 Christina's Picks: Xounds Redux & FruitMenu Redux Hosts: Leo Laporte, Andy Ihnatko, and Christina Warren Guest: Federico Viticci Download or subscribe to MacBreak Weekly at https://twit.tv/shows/macbreak-weekly. Join Club TWiT for Ad-Free Podcasts! Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit Sponsors: PaloAltoNetworks.com/Idira coveron.com/macbreakweekly and use code macbreakweekly cachefly.com/twit

Federico Viticci of MacStories joins the show this week! Federico shares his experience using Apple's new M5 Ultra Mac Studio & running local AI agents with the machine. John Ternus is looking to get the company to run faster & leaner. And AT&T may not support Apple's new iPhone Handoff feature? M5 Ultra Mac Studio Review: The dream Mac for local AI agents. Apple's new CEO seeks to make company run faster and leaner. AT&T seemingly has no plans to support Apple's new iPhone Handoff feature. iPhone 18 Pro Face ID rebooting bug to be fixed in iOS update. Meta announces VR headset for $1299. Picks of the Week Federico's Picks: Open Minis, Cadu Bot, and Comet KVM Andy's Pick: Keychron K3 v2 Christina's Picks: Xounds Redux & FruitMenu Redux Hosts: Leo Laporte, Andy Ihnatko, and Christina Warren Guest: Federico Viticci Download or subscribe to MacBreak Weekly at https://twit.tv/shows/macbreak-weekly. Join Club TWiT for Ad-Free Podcasts! Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit Sponsors: PaloAltoNetworks.com/Idira coveron.com/macbreakweekly and use code macbreakweekly cachefly.com/twit

Episode OverviewOn this Casting Angles episode of The Articulate Fly, host Marvin Cash and Mac Brown, fly casting instructor at Mac Brown Fly Fish in Bryson City, North Carolina, unpack the biggest light bulb moment from Mac's recent casting mastery workshop: casting arc and applied power are inseparable, and many loop problems blamed on "too much power" are really a mismatch between the two. It is a practical lesson for any angler who wants cleaner loops at varying distances, and it arrives just as Western North Carolina anglers face a delayed start to the fall delayed harvest trout season.Mac explains why the same length of line can either unroll cleanly or turn into a tuck cast depending on how much force is applied across a given arc. He stresses reading the pace of the cast and shares a verbal cadence of "slow, slow, slow, fast" for timing the back cast. He also offers a quick yard drill that pairs a very slow stroke with a very narrow arc to show how easily minimal power overwhelms a short casting path. Marvin adds a power calibration drill built around rod noise and backing off until the loop collapses.The second half turns to conditions and news. The North Carolina Wildlife Resources Commission is pushing delayed harvest stocking back a month to early November and stocking fewer fish after a brutally hot and dry summer, a hatchery renovation and heat-related fish kills. Mac celebrates Team USA's first-ever adult men's team and individual gold medals at the world championships in Idaho, led by Michael Bradley of Cherokee, and previews his four-day fall school. Cooler nights and fresh rain are finally dropping water temperatures on Southern Appalachian trout streams such as Deep Creek.Key TakeawaysHow to diagnose a tuck cast by reading the pace of the cast rather than assuming the problem is simply too much power.Why casting arc and applied power must be matched, so that a narrow arc needs far less effort than most anglers expect.How to use a "slow, slow, slow, fast" verbal cadence to time the back cast and stop rushing the stroke.How to find the minimum power for a symmetrical loop by backing off until the loop collapses and then adding just a touch of force back.Why a low frequency whoosh from the rod is an audible sign you are overpowering the cast.When to expect Western North Carolina delayed harvest stocking this fall and why a hot summer and hatchery setbacks pushed it to early November.Techniques & Gear CoveredThe core technique is matching casting arc to applied force: Mac uses the traditional clock face framework, such as a stroke from 10 o'clock to midnight, to show how excess force on a given arc produces a tuck cast instead of a line that simply unrolls. Marvin frames arc length as the runway for acceleration, noting that a longer stroke lets you build speed gradually and that overpowering the final pinky pull on a short runway produces a tuck. Mac's yard drill pairs a very slow forward stroke with a very narrow arc to form a tight loop, then widens the arc until effort and path match for a perfectly straight cast. Marvin's complementary drill uses the low frequency whoosh of the rod as feedback, backing power off until the loop collapses and then adding a smidge to establish a symmetrical foundation. Together the two drills put the caster in charge of both variables: the effort and the length of the path.Locations & SpeciesFall trout fishing in Western North Carolina starts later than usual this year, with the North Carolina Wildlife Resources Commission delaying delayed harvest trout stocking by a month to the beginning of November and planning to stock fewer fish. The delay follows a brutally hot and dry summer, the closure of the Pisgah hatchery for a major renovation in late 2025 and fish kills at the Armstrong hatchery, where hot water on Armstrong Creek was made worse by tree cover lost to Hurricane Helene. Conditions for Southern Appalachian trout are improving, with four straight nights in the mid-40s, a three-inch rain after roughly two months without a significant one and noticeably cooler water on streams like Deep Creek. Marvin also notes that the Tennessee side of Great Smoky Mountains National Park has had plenty of water.FAQ / Key Questions AnsweredWhy does my fly line tuck on the back cast even when I'm not using much power?According to Mac Brown, arc and power are so interrelated that a tuck is often a mismatch between the two rather than simply too much power. With a very narrow arc, even minimal effort can be too much and turn the loop into a tuck. Widening the arc to match the effort you are applying produces a straight cast that simply unrolls.How do you know how much power a fly cast needs?Marvin Cash's drill is to keep backing off the power until the loop collapses, then add back just a smidge of force. That point is the foundation for a symmetrical cast. A low frequency whooshing sound from the rod is a reliable sign that you are using too much power.How should you time the back cast?Mac recommends saying "slow, slow, slow, fast" out loud as you make the back cast, which reflects how long the stroke should take. If the cast is already over by the time you reach the first "slow," you have applied too much force too early. Watching the pace of the cast is the quickest way to see whether timing is the problem.When does delayed harvest trout stocking start in Western North Carolina this fall?The North Carolina Wildlife Resources Commission is delaying delayed harvest stocking by a month, so it will not begin until the beginning of November, and fewer fish will be stocked. The delay stems from a brutally hot and dry summer, the renovation of the Pisgah hatchery and heat-related fish kills at the Armstrong hatchery. Marvin suggests using the extra time for casting practice and skill work on the water.Related ContentS7, Ep 80 - Foundations of Fly Casting: Mastering Variability and Adaptability with Mac BrownS7, Ep 76 - From Repetition to Retention: The Path to Mastery in Fly CastingS8, Ep 7 - Casting Foundations and Fishing Frameworks: Insights with Mac BrownS8, Ep 67 - Elevate Your Cast: Mac Brown's Expert Tips on Haul Timing and Line SpeedS7, Ep 85 - Navigating Delayed Harvest: Mac Brown's Insights on Fall Fishing TacticsView All Casting Angles Episodes with Mac BrownConnect with Our GuestFollow Mac on Facebook, Instagram and Twitter.Follow the ShowFollow The Articulate Fly on Facebook, Instagram, Threads and YouTube.Follow our Substack newsletter for episode updates, tips and resources.Support the ShowShop through our Amazon link to support the podcast.Join our Patreon community to support the show.If you are in the industry and need help getting unstuck, learn more about our consulting options.Subscribe & AdvertiseSubscribe to the podcast in your favorite podcast app.Think our community is a good fit for your brand? Advertise with us.

Federico Viticci of MacStories joins the show this week! Federico shares his experience using Apple's new M5 Ultra Mac Studio & running local AI agents with the machine. John Ternus is looking to get the company to run faster & leaner. And AT&T may not support Apple's new iPhone Handoff feature? M5 Ultra Mac Studio Review: The dream Mac for local AI agents. Apple's new CEO seeks to make company run faster and leaner. AT&T seemingly has no plans to support Apple's new iPhone Handoff feature. iPhone 18 Pro Face ID rebooting bug to be fixed in iOS update. Meta announces VR headset for $1299. Picks of the Week Federico's Picks: Open Minis, Cadu Bot, and Comet KVM Andy's Pick: Keychron K3 v2 Christina's Picks: Xounds Redux & FruitMenu Redux Hosts: Leo Laporte, Andy Ihnatko, and Christina Warren Guest: Federico Viticci Download or subscribe to MacBreak Weekly at https://twit.tv/shows/macbreak-weekly. Join Club TWiT for Ad-Free Podcasts! Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit Sponsors: PaloAltoNetworks.com/Idira coveron.com/macbreakweekly and use code macbreakweekly cachefly.com/twit

En este episodio del iSenaCode Live, hablamos de todo lo que Apple prepara para sus próximos lanzamientos de 2026: nuevos Apple TV 4K, HomePod con Siri AI y una nueva generación de iPad que podría llegar con chip A19 y Apple Intelligence.Repasamos las últimas filtraciones y pistas encontradas sobre el futuro Apple TV y HomePod, además de las novedades que podrían llegar al iPad de entrada y al esperado iPad mini. También hablamos de iOS 27.2 y la llegada de Siri AI en español, una de las actualizaciones más importantes para los usuarios de iPhone, iPad y el ecosistema Apple.En este episodio hablamos de: Nuevos Apple TV 4K y HomePod para 2026Siri AI llegando al HomePod con audioOS 27Nuevo iPad con chip A19 y Apple IntelligenceRumores y filtraciones del próximo iPad miniiOS 27.2 beta pública y Siri AI en españolGemini 3.8 Live Avatar y el futuro de los asistentes

Three months ago Dwarkesh, who has been posting incredible blogs and episodes about RL, posted a framing question for his video essay on RLVR which upset a lot of Computer Use folks:We are no strangers to learning in public and are no strangers to the stress of getting things wrong when you have a big platform. However, we were at Anthropic for the Computer Use launch, there for Claude Cowork with the first big podcast on it, organized the first Computer Use track at AIE presenting the state of the art, and were close to the OpenAI-Sky Software acquisition that now powers the complete domination of computer use that Codex enjoys today. This is why we're excited to bring you today's first guest, Ari Weinstein, cofounder of Sky and now leading all the amazing CUA progress that casuals might miss:Ari explains why Computer Use is now “180 degrees different” from where it was months ago, how agents are learning to debug and recover from failures, why combining screenshots with accessibility data, the DOM, Playwright, and generated code changes the speed equation, and why the next frontier is making agents literally superhuman at using software.OpenAI clones JevIn the second half, Nikunj Handa from OpenAI's API team breaks down the new developer stack: async tool calling, mid-turn steering, WebSockets, UltraFast inference, the Decisions API, prompt caching, pre-warming, compaction, and the Agents API. Given that we were the first Jev podcast, we particularly focus on the unusually fast sprint on the Decisions API:And why it is just a Luna wrapper for now but the team is motivated and egoless enough to clone what they consider to be good patterns.We discuss:* Why OpenAI thinks Computer Use has changed dramatically in just the last few months* Dots and what changes when every agent gets its own Linux computer* Why Computer Use can now complete some tasks faster than the average human* The path from human-level to “literally superhuman” computer use* Why modern agents are much better at debugging and recovering from failure* How screenshots, accessibility trees, the DOM, Playwright, and generated JavaScript work together* App Shots and why they give models much richer context than ordinary screenshots* Why Computer Use can close the loop between writing software and testing it* Trust, permissions, and safety when agents can make payments and operate websites* Async function calling and why models no longer need to stop reasoning while tools run* Mid-turn steering, WebSockets, and the architecture behind more responsive agents* UltraFast inference and how OpenAI is pushing frontier models toward much lower latency* The rapid internal story behind the Decisions API* Why Decisions API is more than structured outputs at low latency* GPT Live, fast tool calling, and real-time computer control* How OpenAI is already using Decisions API for support classification and internal workflows* Longer prompt caching, cache pre-warming, and cache-aware applications* Server-side compaction vs manual compaction for long-running agent threads* What should live inside an Agents API versus a developer's own harness* OpenAI as an “AI cloud” and the search for higher-level primitives beyond raw model APIsAri Weinstein* Product & Engineering, Computer Use at OpenAI* X: https://x.com/AriX* LinkedIn: https://www.linkedin.com/in/weinsteinari/Nikunj Handa* Product, API at OpenAI* X: https://x.com/nikunjhanda* LinkedIn: https://www.linkedin.com/in/nikunjhanda/Timestamps00:00:00 OpenAI DevDay: Dots, GPT-6.1, Agents API, and Decisions API00:02:52 Dots and Personal Cloud Computers00:04:59 Why Computer Use Is “180 Degrees Different”00:06:04 From Sky to Self-Debugging Computer Use Agents00:09:24 How Computer Use Sees and Operates Software00:12:09 From Faster Than Humans to Superhuman Computer Use00:16:03 Agents API: Trust, Permissions, and Safety00:17:31 Computer Use for Coding, Testing, and QA00:19:14 GPT-6 APIs, Async Tool Calling, and UltraFast Inference00:23:21 The Rapid Story Behind Decisions API00:25:32 What Decisions API Is and How It Works00:30:24 What OpenAI Is Building With the New APIs00:32:23 Prompt Caching, Pre-Warming, and API Performance00:35:20 Context Compaction for Long-Running Agents00:37:13 Memory, Higher-Level APIs, and the AI CloudTranscriptIntroduction: OpenAI DevDay and the New Agent StackVibhu [00:00:00]: Okay. We're very excited to be here. Today is OpenAI DevDay. Special podcastSwyx [00:00:08]: We're the first podcast after your livestream.Vibhu [00:00:10]: First podcast. We have Ari here, who leads the product and engineering team for Computer Use agents. Before we kick in and dive deep on Computer Use, you wanna give a quick recap? What was announced? What's the quick slew of announcements you guys had today?Ari Weinstein [00:00:24]: Yeah. yeah, it was a super exciting day. we just got out of the keynote. It was really sick. there were a bunch of Computer Use announcements that I think are worth thinking about. We have, Dots, which is the new, sort of personal assistant product, and, that has some really exciting Computer Use features. There's GPT-6.1 Sol, which is this amazing new model, that I think is particularly great for Computer Use ‘cause of, sort of the cost and speed, advantages. I think, I think we shared that it's, a fifth of the cost of Astra and a seventh of the cost if you're looking at Computer Use specifically, which is really amazing. sorry, there were so many things. I'm trying to sort through it.Swyx [00:01:02]: And the API.Ari Weinstein [00:01:03]: Agents API, which now has Computer Use in it, which is really cool, ‘cause now developers can build on the same Computer Use, that is part of Codex, and ChatGPT. and then there were some demos of our existing Computer Use features, like app shots, where you can take the context of something you're doing on your computer and bring it into Codex and ChatGPT really fast. And then, like, native Computer Use on your Mac, where Roman had it taking screenshots of his app, automatically, and he could do other things on his computer while Computer Use was using his applications. so yeah, really exciting keynote.Swyx [00:01:35]: And not to mention the Decisions API.Ari Weinstein [00:01:37]: Decisions API.Swyx [00:01:38]: Off the bat, are they all the same model? Like, this is. Or the same dataset distilled to different models?Swyx [00:01:44]: Like, basically, like, is Computer Use using Decisions API, or are they, like, kinda separate?Ari Weinstein [00:01:49]: So what's really cool about the Decisions API is it, you know, it has all these new capabilities. It does inference in parallel. it doesn't have reasoning. It's a smaller model, than the ones we use for Computer Use. and so those capabilities make it really fast.Dots and Delegating Work to a Cloud ComputerSwyx [00:02:07]: Yeah.Ari Weinstein [00:02:07]: They also make it a little bit less good at doing, like, long horizon, sort of sophisticated tasks. And so I think I would say it's still an open area of research for how we, like, bring those approaches together. But, yeah, I'm really excited to see what people build with the Decisions API.Vibhu [00:02:24]: One of the interesting things is Dots now have attached personal computers.Ari Weinstein [00:02:28]: Yeah.Vibhu [00:02:28]: So it seems like they're very much more persistent. You've been using them for a while. How should people push the bounds? Like, what should people aim for? What should they try? Personally, right now I use it for a lot of customer service. LikeAri Weinstein [00:02:41]: CoolVibhu [00:02:41]: “Oh, this was wrong. I don't wanna sign in. I don't wanna authenticate.” Find whatever and just get it fixed.Ari Weinstein [00:02:45]: Yeah.Vibhu [00:02:46]: How should we push further? What should people try?Ari Weinstein [00:02:50]: Dots Are a really cool product because each Dot has access to its own Linux virtual computer in the cloud, which is different from our other products. you know, traditionally, we've have access to a browser in the cloud, or it has access to your own computer, but now you get your own entire Linux computer in the cloud. And so it can run full desktop applications, and it can also use a web browser. And so, yeah, you know, I think the powerful thing about Computer Use and the reason why I think it's so, exciting is because it makes it so that the agent can do anything you as a, as a person can do, because all the software in the world was designed for humans, and now agents can use that same software, and you can delegate to the agent. So, yeah, like, anything that you would do on a computer, you can ask a Dot to do. Yeah, I think what particularly is useful is gonna really depend on who the end user is and what- what's valuable in their life. but yeah, I would just start by thinking about, like, one of the things that you spend time on and how could you delegate those to an agent.Swyx [00:03:47]: Yeah, a lot of flight booking and shopping and honestly even, like, playing a game or whatever, right?Ari Weinstein [00:03:52]: Totally.Swyx [00:03:52]: Yeah.Ari Weinstein [00:03:53]: Yeah, I don't know. For me, something I did recently, I've been working on. I've, subscribed to a meal prep service ‘cause I was trying to, like, eat healthy, you know? And I really like this meal prep service I found because it lets me customize the meals I order to, like, a high degree of granularity. So I can say, like, “I want this many grams of chicken and this many grams of rice.” but it was so complicated. It took me two hours to do an order, and I found that I could ask Computer Use to do it for me, and it did it in 15 minutes. so I actually saved two hours. it both did it eight times faster than I could, and it saved me two hours on GPT-6.1 Sol.Swyx [00:04:32]: Yeah.Ari Weinstein [00:04:32]: So those are the kinds of tasks that I feel like, are really powerful.Swyx [00:04:36]: As a creator, I can tell you automatically, immediately, my number one use case is automating YouTube.Ari Weinstein [00:04:40]: Nice.Swyx [00:04:40]: Because, YouTube doesn't expose a lot of things via API.Ari Weinstein [00:04:43]: Yeah.Swyx [00:04:43]: And you have to just put it in a VM and just, like, run it, for, like, let's say, let's say their AB testing feature or making community posts. None of this is available by API ‘cause they hate developers.Swyx [00:04:53]: Anyway, so,Ari Weinstein [00:04:55]: I've heard that from our developer experience team too. They use it with YouTube a lot. Yeah. It's really awesome.Swyx [00:04:59]: So I wanna draw for, you know. let's say, I wanna get a little bit spicy. One of our, the leading AI podcasts, our friends, is famous for saying that Computer Use hasn't advanced in the last two years.How Computer Use Has Changed in the Last YearAri Weinstein [00:05:12]: Yeah.Swyx [00:05:13]: Which is a very interesting statement, and I think you're one of the best people in the world to talk about this, like, how have things have progressed, right?Ari Weinstein [00:05:20]: Yeah. You know, they said that a few months ago, I think, and I hope they have a different perspective now because Computer Use is, like, 180 degrees different than it was.Swyx [00:05:26]: He's a, he's a tough guy to impress.Ari Weinstein [00:05:27]: Yeah, okay. well, we're working on it.Swyx [00:05:30]: But, you know, you worked on. You've, like, basically spent your whole career working on, like, some kind of computer automation, right?Ari Weinstein [00:05:34]: Yeah.Swyx [00:05:34]: Like shortcutsAri Weinstein [00:05:35]: YeahSwyx [00:05:35]: At Apple, and then Sky, and then, and then joining OpenAI. Can you draw, like, what your through line is for, like, what is driving you and what- you, what wasn't possible back then maybeAri Weinstein [00:05:47]: Yeah.Swyx [00:05:48]: And, like, what your sort of milestones were.Vibhu [00:05:49]: I guess to add on to that as a follow-up question, what's the major change from using Codex Computer Use from, like, last weekAri Weinstein [00:05:57]: YeahVibhu [00:05:57]: Through to today? Is it model? Is it dots? Is it harness? So all the history plus what really just changed in today's announcements?Ari Weinstein [00:06:04]: Yeah. On the through line, I guess I've always been excited about automation and helping people automate tasks because then you can, like, save time in your life and focus on things that are more important to you than, like, operating a computer very intricately. And so, yeah, that was why we worked on some of those products. I was at Apple before. we made a company called Sky. we ended up joining OpenAI, which is really exciting. and I think something that wasSwyx [00:06:27]: And almost like you have to hack around Apple until Apple was like, “Fine, like, we'll just hire you and you can just work on the inside,” right? Like.Ari Weinstein [00:06:35]: It was, it was a cool place to get to work. what was really interesting looking back at Sky is we were, we were working on Computer Use there as well, and the models were so much less capable. And now the models, just in the last one year, have become extraordinarily capable at Computer Use. I think the biggest delta that I see is before they could, like, reliably start tasks, but then they would run into problems, and now they're really good at debugging. They're really good at trying again, introspecting what is and isn't working. and I think we've also brought the Computer Use the Computer Use field itself has moved forward. I think we're using more techniques. now Computer Use, often writes code. So if you actually look at it in Codex and you expand the tool calls manually, you can see that it's not just doing one action at a time. It's actually writing JavaScript code that it executes, that the computer executes to perform sometimes many actions at once, which is a great, you know, speed up and great capability. We use more accessibility, sort of multimodal interfaces. So, the model may use screenshots, it may use accessibility, it may use Playwright. it can use a lot of different mechanisms, based on the task at hand. and then, yeah, the model acceleration has been, has been just amazing. So, yeah, what's different today? I think we're making computers better all the time, so I think just, like, one day's difference, is probably a little bit less consequential than, like, even the past month or the past two months. but, yeah, I think the Computer Use in Dot is really exciting as well as, the new model that we came out with.Measuring Computer Use and Improving the HarnessVibhu [00:08:03]: On the keynote, Tejal was mentioning 7x improvements in Computer Use speed, a lot better on a few benchmarks. How do you guys think about measuring it? Computer Use is one of those things where, as you say, you know, it's improvements over time.Ari Weinstein [00:08:20]: Yeah.Vibhu [00:08:20]: Is it harness? Is it model? Is it post-training?Ari Weinstein [00:08:22]: Right.Vibhu [00:08:22]: How do you guys look at it internally about measuring how good it is, and what were the changes with the new model?Ari Weinstein [00:08:29]: We actually have a bunch of different ways of measuring it, some of which are on different permutations and configurations of the harness. It's a bit of a complicated story because, you know, our production products have, you know, some more safety checks, and, you know, those are configured differently based on the needs of the, of the task at hand. So there's a lot of ways to measure it, but I think regardless of how we measure it, we find pretty consistent gains. and those gains are, sometimes in the harness and sometimes in the model. and yeah, I was really excited by this result that GPT-6.1 is even more cost-effective for Computer Use than its baseline cost improvement as compared to Astra. It's, like, really cool to see.Swyx [00:09:10]: Yeah. I mean, one of the visuals I really liked from the livestream was that, you're sort of improving the Pareto frontier of, your, curve, and there was a lot of talking about how you're improving it together with the harness.Ari Weinstein [00:09:24]: Yeah.Swyx [00:09:24]: Can you give some examples of aha moments that you had, whether it's on, like, model driving the harness driving the model, whatever?Ari Weinstein [00:09:32]: I don't mean to repeat myself, but I think, like, introducing more modalities has been really powerful.Swyx [00:09:36]: Okay.Ari Weinstein [00:09:36]: One more specific example of that is, in the past, I think we saw a lot of Computer Use, products had to spend a lot of time, like, scrolling, you know? So it would, like, take a screenshot. It would try to do something. It would be like, “Oh, I gotta, like, scroll down to the next page of results,” and then it would take a screenshot, and then it would try to do something. It would scroll down again. And so I think, with accessibility and other. and, direct access to the DOM and other things like that, now the language model can actually see, like, an entire page or an entire application. It can write code that can do multiple steps at once. And so I think those have been probably the biggest single aha moments. There's, like, a lot of tiny ones that are less exciting in comparison, but actually we do find also that a lot of speed improvements are driven by, like, a lot of little paper cuts that we gotta go in and introspect.App Shots, Accessibility, and Better Computer ContextSwyx [00:10:21]: Yeah. A lot of really hard engineering.Ari Weinstein [00:10:23]: Yeah.Swyx [00:10:23]: I mean, app shots in general, right? Like, I think people don't quite get the difference if. because there's, like, a nice visual in Codex when itAri Weinstein [00:10:30]: YeahSwyx [00:10:30]: When you take an app shot, but they don't maybe they get the difference that, you are able to actually drive each button and you have the, you have each text, in a very optimal representation.Ari Weinstein [00:10:40]: Yeah. Exactly. Yeah. It's kind of fun actually. If you wanna be, like, really nerdy about it, you can go into Codex, take an app shot by hitting the two command keys. So you grab the content from whatever app you're working with, bring it into the, Codex or ChatGPT chat. And then the. if you click on the attachment and you click on this, like, little tiny button in the top right, you can see the raw text and you see the raw accessibility representation. And yeah, we've put a lot of work into, puttingSwyx [00:11:04]: Just dumping everything out. Yeah.Ari Weinstein [00:11:05]: Dumping it out, but also making it token-efficient, doing it efficiently. There's, like, a bit of an art to it. And, you know, it turns out that the same technology that was invented for humans, you know, who maybe have accessibility needs, who wanna use a screen reader technology, that technology is really helpful for them to be able to use computers. It's also really helpful for LLMs to be able to use computers. So that's been, like, really fun to get to work on.Vibhu [00:11:27]: For context, I feel like a lot of people don't understand app shots. They don't even know it's a feature.Ari Weinstein [00:11:30]: Yeah.Vibhu [00:11:31]: It's when you double hit command, it pulls in what looks like a screenshotAri Weinstein [00:11:34]: RightVibhu [00:11:34]: And you're like, “Oh, why have I opened up just a screenshot and thrown it in?” No, it's actually pulling all the metadata, all the code, everything.Ari Weinstein [00:11:40]: Yeah, exactly. Yeah. So it's like, you know, if you take a screenshot of a webpage that has a link- The screenshot doesn't include where the link goes. It doesn't include, you know, maybe you take a screenshot of your calendar, the ca- event ti- titles are truncated, you know? But when you take an app shot, it gives, like, the language model, like, full context about everything and, that lets it, just sort of, like, do much more.Swyx [00:12:02]: Yeah. For those who wanna see more, Jason Liu, I invited him to do a full workshop on this, at AI Engineer.Ari Weinstein [00:12:07]: Amazing.Swyx [00:12:08]: Did a great job.Vibhu [00:12:09]: I have a broader vision questionToward Superhuman Computer UseAri Weinstein [00:12:11]: YeahVibhu [00:12:11]: On Computer Use agents. So your example of take a screenshot, scroll page, take a screenshot is where we were.Ari Weinstein [00:12:17]: Right.Vibhu [00:12:17]: Today, they can automate a lot. what are the bottlenecks? Is it models? Is it harnesses? What. Where do you see it going in, like, two years? Do you see it just running for hours? How do we get there? Any predictions on where Computer Use goes?Ari Weinstein [00:12:32]: Yeah. I mean, I think what's really crazy that I think, You know, the team's accomplished over the past couple of months is that now Computer Use is, like, faster at accomplishing tasks than, like, the average human probably in most cases. and I think that the next frontier is to have Computer Use be, like, literally superhuman in its performance where it actually is as fast or faster at using software than, like, expert Computer Users like us. and I think that'll be really consequential and exciting when that happens because I think we'll be able to all of a sudden build products, that, provide just much more real-time experiences. And I think it'll also. lowering the barrier to entry of, or the activation energy, I suppose, of using Computer Use I think will make us start to default to doing certain things in agents that we've become accustomed to doing manually. And I think that's exciting also ‘cause it'll save us a ton of time. and I think there's a, you know, there are a lot of different little paper cuts and bottlenecks that are sort of standing in the way of that. I think that there's, yeah, there's things on the model side, there's things on the inference side, there's things on the harness side, there's things in the, in the representation. You know, we find that as Computer Use gets faster, we're increasingly bottlenecked by just, like, the speed of doing an operation. Like, for example, you know, a non-trivial amount of time in our benchmarks of Computer Use tasks is actually, like, let's say you're automating a task on doordash.com. Like, a lot of the time is actually waiting for doordash.com itself to load, you know?Swyx [00:14:04]: Yeah, then you just write a wait and then you execute the wait.Ari Weinstein [00:14:07]: Yeah, totally. And you wanna get. Yeah, actually, it's actually really important that you get that de- like, you want as little delay as possible between when it finally finishes loading and when you go andSwyx [00:14:16]: YeahAri Weinstein [00:14:16]: Trigger the LLM to do the next action, which is actually- itself a statistical science.Swyx [00:14:20]: Like an event-driven way maybe to do that.Ari Weinstein [00:14:22]: When possible, you want it to be event-driven.Swyx [00:14:24]: JavaScript has some load events.Ari Weinstein [00:14:25]: And JavaScript has load events for. or the web browser has load events for web navigation, but there's other types of events that actually really can't be event-driven. So there's a lot of complexityVibhu [00:14:34]: The one that comes to mind is, like, chatting with customer service.Ari Weinstein [00:14:37]: Yeah.Vibhu [00:14:37]: Replies could take 30 seconds, could take three minutes.Ari Weinstein [00:14:39]: Oh, right.Swyx [00:14:41]: I have dealt with so many bots with Codex. it's great, but I also wonder if the other side knows that they're talking to a bot ‘cause I'm, like, answering in complete sentences. Like, I'm capitalized correctly.Ari Weinstein [00:14:50]: That's hilarious.Swyx [00:14:51]: Like, I'm giving full num- full reference numbers and everything. Like, it's too. it's clearly too good. I don't care. Like Like, I'm just, like, trying to get my support case.Vibhu [00:14:58]: I've prompted it to, like, you know, “Don't pretend you're a bot. Be very annoyed human.”Vibhu [00:15:02]: Short one-liners, likeSwyx [00:15:04]: YeahVibhu [00:15:04]: Push it, do all this. I also tell it, “While you're waiting for responses, like, use subagents to research better ways to figure out what we need.”Ari Weinstein [00:15:12]: Nice.Vibhu [00:15:12]: It's just, like, human little intervention.Ari Weinstein [00:15:14]: That's awesome. I also feel like half the time it's a bot on the other end, so now youVibhu [00:15:17]: YeahAri Weinstein [00:15:17]: Got the bots talking to each other.Swyx [00:15:18]: Yeah. I will also say, you know, like, you know, one milestone of Computer Use that we are, we're at now is, you know, three, four years ago, we were scared of hooking up LLMs to the, to the web and toAri Weinstein [00:15:31]: YeahSwyx [00:15:31]: To our, to our devices. And now I'm having it configure DNS for me.Ari Weinstein [00:15:35]: Wow.Swyx [00:15:36]: I'm having it pay my bills, and, like, really, like, tens of thousands of dollars of, like, stuff I'm just sending it over and yoloing with Computer Use and, like, you know, what's the, what's the worst thing that can happen?Swyx [00:15:48]: So that- that's all, that's all really good.Building Safely With Computer Use in the Agents APIAri Weinstein [00:15:50]: Yeah.Swyx [00:15:50]: I think now that you've. you know, obviously, you also have to dogfood your own products and all these things. Now that you've sort of released this in API, what are some pitfalls or tips that you wanna tell developers, because they're about to, I guess, encounter all this, firsthand?Ari Weinstein [00:16:03]: First of all, I'm just really excited that we brought Computer Use into the Agents API. I think this is, really great because obviously a lot of developers are building applications that wanna be able to work with third-party websites and services. And so Computer Use has this universality to it. It can work with anything. So now all of a sudden, developers can build using the same Computer Use implementation that we're building on. I think there's great work to be done if you wanna build your own Computer Use harness, but it's hard. And also, we train our models on our Computer Use harness, so there is, an advantage to using the one that's in distribution for the model. There actually might be a speed and cost and accuracy advantage. So I think it's really great for people to get to build on top of that. And, yeah, you know, I think kind of to the point that you were making, like, I think we're all sort of still in the process and maybe, like, some of us are ahead of many people in the world of, like, getting comfortable with this technology and trusting it. And so I think it's incumbent on us to, sort of build that trust over time by making sure we're building things that are reliable, by building, the right kinds of safety checks, by asking for the user's consent before doing something consequential like making a payment, by, asking, you know, maybe depending on the application, making sure you're only letting it access the websites or applications that it actually needs for the task. So that's, I think, something important to think about. but yeah, I'd really encourage people to try the new Agents API, build all kinds of cool stuff on it. We'd love to hear your feed- feedback if, you know, depending on how it goes.Vibhu [00:17:31]: Have you seen any changes in the way it affects dev workflows? So one of the things with dots is, you know, you're seeing it in Slack.Ari Weinstein [00:17:38]: Yeah.Vibhu [00:17:38]: You're seeing people use voice and build. the example Roman showed of change this app and send me screenshots along the way and all this.Computer Use for Testing and Closing the Software LoopAri Weinstein [00:17:46]: Yeah.Vibhu [00:17:46]: Is anything that you're seeing there in adoption about how people are using Computer Use for coding workflows? Any tips people should take from that?Ari Weinstein [00:17:55]: One of my favorite use cases for Computer Use actually, and one that we see a lot in the wild, is Computer Use letting the agent- actually test the software that the agent has built, which is far more consequential than it sounds. Because traditionally, you know, you'd build something in Codex and then the-- and the Codex builds it for you, and then you have to test it, and you are now like QA for the agent, right? So with Computer Use, you can complete the develop-- the software development life cycle, where, the agent can build software, it can test it. So I have a lot of fun, you know, building stuff, having the agent test it. By the time it comes to me, it's already working. I have, extra fun because sometimes I'm, like, developing Computer Use itself, and so now I have a Computer Use agent that's using my Computer Use agent that's using something else. so yeah, I really, I really think this is a super powerful class of use case.Swyx [00:18:44]: I have a visual play test skill that I've developed that, really catches a lot of design issues,Ari Weinstein [00:18:49]: NiceSwyx [00:18:50]: That, you know, normally when you just look at code, you wouldn't really pick it up. it's also really good for cloning apps, though. If you're using a shitty SaaS and you wanna kill the SaaS You just clone it screen by screen by screen. and Obviously, Computer Use can completely drive everything, take screenshots, note it down, and then clone everything with Codex.Ari Weinstein [00:19:06]: That's really cool.Swyx [00:19:06]: But yeah, thanks for all your progress. I think, that isAri Weinstein [00:19:08]: AbsolutelySwyx [00:19:09]: Our time.Nikunj Handa: What's New in the OpenAI APIAri Weinstein [00:19:10]: Yeah.Swyx [00:19:10]: This is not the last that we're gonna talk.Ari Weinstein [00:19:12]: Yeah, cool. This has been really fun. Thank you guys for having me.Swyx [00:19:14]: All right.Vibhu [00:19:14]: All right. Okay, we're a strict cutoff. We're just gonna dive right in.Nikunj Handa [00:19:17]: Let's do it, yeah.Vibhu [00:19:19]: Okay, so, Nikunj, we're very excited to have you. You shipped a lot on the API side, like we justNikunj Handa [00:19:25]: YeahVibhu [00:19:25]: Talked about with Ari. You can now build with Computer Use agents. Anything you wanna highlight, the API side of changes, and introduce yourself a little and what you do?Nikunj Handa [00:19:34]: Yeah, for sure. My name is Nikunj. I lead product for the API team. Been here for roughly three years. been working on launching models. I feel like that's just been, like, a thing, constant thing throughout my time, here at OpenAI. And, with every new model, we try to, like, basically work super closely with the post-training team, the research team, to figure out what's new in it. and then we, like, expose those capabilities in the API. so that's, like, the basic way of putting it. and if you just look at, everything that's new with GPT-6, the cool new capabilities that we launched were, firstly, async function calling. so what you see with, like a lot of the things that you're seeing in, like, Codex and Dots and everything is that tool calls take so long that you don't have to, like, pause the model's execution while, the tool is running. So you could just, like, kick off a tool call, keep running, keep reasoning, and then check back in. so we launched async tool calling. We launched, like, mid-turn steering, so now you can, like, inject messages while the model is reasoning, in the middle. so as your tool call finishes, you can put in that instructions.Async Tool Calls, Mid-Turn Steering, and WebSocketsSwyx [00:20:43]: And that's also partially a model alignment capability, right?Nikunj Handa [00:20:46]: Yeah.Swyx [00:20:46]: Like, they have to train in the ability to train.Nikunj Handa [00:20:48]: Exactly, yeah. AndVibhu [00:20:49]: I feel like we've had it in the app. You could always, as it's reasoning, you could steer.Nikunj Handa [00:20:54]: Yes.Vibhu [00:20:54]: It wasn't the best. It's gotten much better.Nikunj Handa [00:20:57]: Yeah.Vibhu [00:20:57]: Excited to see how it does this in versionNikunj Handa [00:20:58]: Yeah, and I like our mainVibhu [00:20:59]: And nowNikunj Handa [00:21:00]: Goal in, our main goal in the API is to, like, put things in the API once it's trained into the harness. And so we kinda wait for that moment until it's good enough. And a lot of that is, like, actually being powered by WebSockets, which we launched, a few, I wanna say months ago. And so WebSockets just opens this, like, whole bidirectional, like, communication thing with the model. This is not, the GPT Life thing. I'm just talking about GPT-6. and you can do all these, like, async tool calling, async reasoning, injecting messages. It's a really fun API to work on. I think, like, really enjoying.Swyx [00:21:33]: Yeah. This is why we are the engineering podcast, because we get to talk about WebSockets.UltraFast and the Inference StackNikunj Handa [00:21:36]: Yeah.Swyx [00:21:37]: This also pairs very well with UltraFast, right?Nikunj Handa [00:21:39]: Oh, yeah.Swyx [00:21:39]: Like, that is now, like, I think for the first time ever available in the API.Nikunj Handa [00:21:43]: Yes.Swyx [00:21:43]: Which is, which is basically the theoretical fastest speed you can ever get, Frontier of Intelligence.Nikunj Handa [00:21:49]: Yeah. It's been so exciting to work on that project. I think, before I go into the API, the most fun part of, UltraFast has been just watching the inference team cook with Astra. Like, they're just, like, constantly having these, like, Codex agents running, trying to, like, squeeze out more performance. And, I would say, like, at least for a couple of months, a lot of it was focused on efficiency and driving the cost down, which is how we, like, were able to cut the Luna price by, like, 80%. It was, like, a lot of that was driven by, like, all the inference improvements they landed. And then now they've, like, shifted gears towards, like, how can we make this run as fast as possible? And so UltraFast has just been, like, amazing to see on a mo- on a model like Astra. Like, to go that fast has been really cool. And yeah, WebSockets is like. actually it was like the first time we launched WebSockets, it was for GPT, 5.3 Codex Spark, which was. Can't believe we named a model that, but, you know, that's what we launched it for. And obviously, it helps so much because, like, you gotta have the tool calls. you had, like, really reduced the overhead, of going back and forth with tools. And so, WebSockets is awesome for that.Swyx [00:22:57]: Yeah. it's always cute to see, like, I have my reset usage limit, and then I have my Spark usage limit that I never use.Nikunj Handa [00:23:03]: Yeah.Swyx [00:23:04]: Like, it's there if I want it.Nikunj Handa [00:23:05]: I think it's gone finally.Swyx [00:23:06]: It's gone. It's gone, yeah.Nikunj Handa [00:23:07]: I know it's gone, so.Swyx [00:23:08]: Yeah. you're slowly killing off all the, you know, theNikunj Handa [00:23:11]: The old ones, yeah.Swyx [00:23:11]: Oldies.Vibhu [00:23:11]: This is a great week. I mean, it was the first time we had Frontier Intelligence at extreme speeds.Nikunj Handa [00:23:17]: Yeah.Vibhu [00:23:18]: People really liked it.Nikunj Handa [00:23:19]: Yeah.Vibhu [00:23:19]: SoSwyx [00:23:20]: YeahVibhu [00:23:20]: First time it comes back.Swyx [00:23:21]: Yeah. for, 5.3 Spark is explicitly attributed to Cerebras. You guys are not confirming or denying that, UltraFast is related to Ce- Cerebras, but people are. I'll just say that people do care and, are wondering about it. And you have your own silicon as well. elephant in the room, decision models.Decisions API: OpenAI's Fast Decision ModelNikunj Handa [00:23:38]: Oh, yeah.Swyx [00:23:38]: Decisions API. We were the first podcast to do a big Jev, deep dive with, Diogo, and I also, you know, featured him at AI Engineer. How quickly did you see Jev and go likeNikunj Handa [00:23:49]: Oh my gosh. Yeah.Nikunj Handa [00:23:50]: Yeah. Firstly, like, huge props to Diogo and, like, the Jev team for, like, really inspiring theSwyx [00:23:55]: YesNikunj Handa [00:23:55]: Like, whole segment in the market. Like, obviously Jev comes out, everyone's, like, losing their minds over it. Our users are, like, hitting us up. But also, like, our internal teams are like, “We need, like, a much faster classification system.” We can. I don't wanna, like, get ahead of some of the dots features that are gonna comeSwyx [00:24:16]: WhooNikunj Handa [00:24:16]: But you're gonna see, like, some cool, like, really snappy, fast things built on top of the decisions API. but, you know, like, yeah. Props to Jev for, like, inspiring this whole thing. obviously a bunch of people at OpenAI get nerd sniped by that, and they're like, “How can we, like, make this work? We're not gonna, like-”Swyx [00:24:33]: Okay.Nikunj Handa [00:24:33]: “. train a new model.” ButSwyx [00:24:34]: Like, four weeks ago, this was not on the dev radar, right?Nikunj Handa [00:24:37]: No, not at all. No.Swyx [00:24:37]: Okay.Nikunj Handa [00:24:37]: This is likeSwyx [00:24:38]: WowNikunj Handa [00:24:38]: Jev-inspired and, likeSwyx [00:24:40]: I think you are officially the first one to your lab to, like, clone and, adopt this.Nikunj Handa [00:24:44]: Yeah. Yeah. I feel like, OpenAI has such a strong, like, hacker culture and, like, people are just, like, they get excited about things. And so, guy from inference, this one awesome guy from, the infra team are like, “ this is amazing. We're gonna, like, hack on it.” They build a prototype, it, like, works, and now we- we are just, like, hill climbing on latency and trying to make this as fast as possible, and we wanna, like, launch it in the coming days. so as soon as we hit our, like, latency target, we'll try to get this out.Vibhu [00:25:13]: It's interesting. At the same time of hacker culture, you also, as Sam said, like 99%, one of the most reliable APIs withNikunj Handa [00:25:20]: Mm-hmmVibhu [00:25:20]: I think probably the most usage, which is your team directly. how should people see decisions API? I feel like a lot of people saw Jev, heard the buzz, haven't built with it. You're making it very mainstream.What Decision Models Are Good ForNikunj Handa [00:25:32]: Mm-hmm.Vibhu [00:25:33]: What should people see it as? How should they use it?Nikunj Handa [00:25:36]: Yeah. I think the main use cases we've seen is, like, really fast classification. all the Computer Use demos have been amazing and really cool. I think there will be limitations, of course, in terms of, you know, having Astra, like, write, like, a JavaScript-like script to control your computer, versus having Luna pick, like, one action at a time. I think, it's not gonna be at the same intelligence level, but, like, maybe there's some Computer Use tasks that this is good enough for. So excited to see that come through. the other cool prototype I've seen internally is people hooking it up with GPT Live. So GPT Live is like, you know, our bidirectional, like, real-time,Swyx [00:26:14]: VoicingNikunj Handa [00:26:14]: A- API. And, it's built on this, like, model of front-end models and back-end models. So GPT Live is this, likeSwyx [00:26:20]: Think or talkerNikunj Handa [00:26:21]: Super fast. Yeah, think or, talker thing. So GPT Live is the talker, super fast, really good at delegation, and you have something like Astra sitting at the ba- at the back. But tool calling has always felt, like, really slow in GPT Live. and so people have been, like, putting together these, like, tool calling demos of GPT Live controlling a computer, and it just feels like so much more snappy and natural. So I'm, like, kinda excited to see, like, what people do with Live and with Luna on decisions API. so that'll be pretty exciting. Yeah.Swyx [00:26:55]: So I wanna iron this out for people, especially from the product side, because a lot of people have been putting out Jev clones. There's been about 100 in the last two weeks.What Makes a Decision Model DifferentNikunj Handa [00:27:01]: Oh, really? That's amazing.Vibhu [00:27:03]: The first couple days.Swyx [00:27:04]: But like, it. Like, they can clone a Jev API, which is honestly structured outputsNikunj Handa [00:27:09]: YeahSwyx [00:27:09]: Which OpenAI was first to.Nikunj Handa [00:27:10]: Yeah.Swyx [00:27:11]: Right? So, like, I think let's iron out for people what is a decision model, as far asNikunj Handa [00:27:16]: YeahSwyx [00:27:17]: As far as, like, what is important? It is not just latency. It's not just structured output, right? Because I could just have Luna as it'- The decision model is priced the same as Luna, right?Nikunj Handa [00:27:26]: Mm-hmm.Swyx [00:27:27]: Have turned off reasoning and then have structured output. Do I have a Jev? you know, no, right? And that's theNikunj Handa [00:27:33]: YeahSwyx [00:27:33]: That's the realVibhu [00:27:34]: There's a confidence there.Swyx [00:27:35]: Yeah.Nikunj Handa [00:27:36]: Yeah, totally. I think, the way that. So we haven't trained, like, a new model for this.Swyx [00:27:40]: Yeah.Nikunj Handa [00:27:40]: We're, like, building this purely on top of the same Luna weights that we have.Swyx [00:27:44]: Oh.Nikunj Handa [00:27:44]: So yeah. This is, like, really just Luna. And, on top of that, what you're doing is you're constraining. So, like, structured output's a big part of it. you're really optimizing the inference stack to, like, get very fast on TTFD. And because you can have multiple questions, what you do is, like, you basically run those in parallel,Swyx [00:28:05]: As a batch.Nikunj Handa [00:28:06]: Yeah. You run those in the-- as a batch. you-- All sorts of, like, inference techniques people are working on to try to make it as fast as possible. But I'd say, like, at least our implementation of it at the start and this first version is, like, zero-shotting this on top of Luna, to see how it goes. And obviously, you wanna, like, put it out there. Like, this is OpenAI's, like, classic iterative deployment thing. Put it out there, see what people think, and then, like, we'll make more model improvements, as needed. so yeah. That's, the decisions API.Swyx [00:28:38]: Yeah. And, obviously as a benefit, you have vision. They don't have vision, right?Nikunj Handa [00:28:42]: That's true.Swyx [00:28:42]: Obviously, Jev's comes withNikunj Handa [00:28:43]: Yeah. Like, we get it for free with Luna. Yeah.Swyx [00:28:45]: Yeah. I do think that, like, you know, some of the innovations, it sounds like, it's still to come if it's still the same Luna weights, which is, like, the confidence stuff, like, the in calibration is something that we've talked about on the podcast with, benchmarking calibration. ‘Cause basically, the whole point is that RLHF kind of collapses you towards what you want to hear.Calibration, Architecture, and the Open Research QuestionsNikunj Handa [00:29:03]: Yeah.Swyx [00:29:03]: But, like, not actually, like, what the amount of confidence is.Nikunj Handa [00:29:06]: Yeah. Yeah, totally. I'm eager to see how it pans out. Maybe there's, like, gonna be. These are gonna be, like, the key areas where we may have to, like, hill climbSwyx [00:29:15]: YeahNikunj Handa [00:29:15]: With the, with the future model release. But, yeah.Swyx [00:29:18]: And then architecture-wise, the other thing that's in the debate, obviously, you-- Nobody knows because Jev doesn't talk about it, but the two speculations are, one, maybe diffusion model instead of autoregressive.Nikunj Handa [00:29:28]: Mm-hmm.Swyx [00:29:29]: But you are able to achieve the parallel, generation in your way. And then the other one is some mech interp type thingNikunj Handa [00:29:37]: Mm-hmmSwyx [00:29:37]: That you're, like, analyzing the activations and then just outputtingNikunj Handa [00:29:40]: That would be coolSwyx [00:29:41]: The weights.Nikunj Handa [00:29:42]: Yeah.Swyx [00:29:42]: Which, like, you guys have all done the research on this. People have speculated.Vibhu [00:29:45]: There have been demos onSwyx [00:29:46]: YeahVibhu [00:29:46]: Both of these as well. I think Gemini shared a Gemini diffusion, Gemma diffusion on a Jev-style output.Nikunj Handa [00:29:53]: Oh, sick.Vibhu [00:29:53]: And, interp people have also, you know, pulled out interp from a middle layer, but this is all speculation.Swyx [00:29:59]: It's just like, what are you trying to aim for, right? Because you can achieve the API. Everyone can achieve the API. It's actually pretty trivial. But, like, then there's the speed, then there's the accuracy, then there's the other calibration features.Nikunj Handa [00:30:11]: Mm-hmm.Swyx [00:30:11]: I don't know what else.Nikunj Handa [00:30:13]: Yeah. Yeah. No, totally. It's so cool that this, like, whole space has been kicked off now and people are gonna do so much cool stuff and everyone's gonna learn from each other. And, yeah, I'm excited about it.What Developers Should Build NextVibhu [00:30:24]: I feel like being on the platform team, a lot of your job is to empower builders.Nikunj Handa [00:30:27]: Mm-hmm.Vibhu [00:30:28]: What do you think people should build with decisions API and also Computer Use agents? Any stuff that you've- been building with internally that you think really opens up after the new change?Nikunj Handa [00:30:39]: Yeah. okay, let's think. decisions API, use cases internally have been pretty obvious. Like, the user ops team was, like, jumping on it. We were like, “We gotta classify all of our support tickets.” what else came up? obviously, there were, like, the really cool GPT Live demos. I'm sure, like, the Codex app team might, like, pick this up and try to do something cool with it. So, you know, like, this whole thing started, like, a week ago, so it's, like, very early andSwyx [00:31:06]: Oh, one week.Nikunj Handa [00:31:07]: We're excited. Yeah. Yeah, pretty much.Vibhu [00:31:08]: There was a big push in, evals, LLM as a judge having really low latency there.Nikunj Handa [00:31:13]: Right. Yeah. That'll be interesting to see. and then, with the Agents API, we have-- we're basically, like, having a bunch of first-party products, like, at OpenAI built fully on top of it. we've had the Codex security stuff that just went out that's fully built on top of, the Agents API. We have, sort of the-- we- we are having, like, a meetings type of thing launching today.Agents API and OpenAI's First-Party ProductsSwyx [00:31:40]: Mm-hmm.Nikunj Handa [00:31:40]: I think there was, like, a demo. do you remember, like, the plugin extensions when Sam was showing it? There was, like, a demo for, like, you're in a calendar, you can sort of, like, have your meeting notesSwyx [00:31:51]: Like, drop into a singleNikunj Handa [00:31:52]: Flow into like your spaceSwyx [00:31:52]: Like, Google Docs type thing.Nikunj Handa [00:31:53]: Yeah.Swyx [00:31:54]: Right?Nikunj Handa [00:31:54]: And so the-- all of that stuff is, like, fully built on top of, the Agents API. and yeah, I'm, like, just excited to see. Like, we're just getting this out, and let's see what people build on top of it.Vibhu [00:32:04]: I think you showed it off very well. The whole edit spaces, pages, collaborate, add in your dot. Like, that's a lot, soNikunj Handa [00:32:12]: YeahVibhu [00:32:12]: There's a lot of inspiration people can go to.Nikunj Handa [00:32:14]: Yeah. All possible with Astra, you know. Like, thing- things just move so fast now. LikeSwyx [00:32:19]: YeahNikunj Handa [00:32:19]: People go from idea to execution so quickly, it's amazing.Swyx [00:32:23]: Is there something that you want, people to focus on to give you feedback? Like, what-- like, you know, maybe you're just putting this out there and you want-- and there's, like, a fork in the road and you want developers to help you decide.Responses API Performance and Long-Lived CachingNikunj Handa [00:32:35]: So I think Agents API and decisions API, they are like, these are our newest products. Would love, like, any and all feedback on that to figure out where to take them. I think, over here, we're, like, very open on Responses API, which is sort of like our workhorse over here. like, really focused on performance right now, and the performance comes in, like, two main ways. first is just, like, latency. We've been, like, rewriting the whole Responses API stack to, like, make it as fast as possible from a TTFT perspective, DVD perspective. So there's like-- that, like, continues to be, like, a main area of focus for us. The second thing we've been trying to do is, like, really go deep on caching, particularly with these, like, personal agents that are, you know, like, basically, like, a single thread that just goes on and on forever. We've been, trying to, like, really up our game on caching. We provide now guarantees of, like, cache hits within, like, 30 minutes. We're actually, like, we-- for one of our users, we just launched, like, a much longer cache window. So we have, like, a 12-hour caching guarantee, that we offer so that you have, like, guaranteed cache hits forSwyx [00:33:40]: Is that a public API?Nikunj Handa [00:33:42]: Not yet. That's in preview.Nikunj Handa [00:33:43]: We're gonna, like, try to get that out to everyone as soon as possible. But, like, just pay a little bit more for the cache write, and we, like, guarantee, like, cache reads for, like, a much longer period. So even if, like, your instinct thread, for example, like, you just, like, do something on it and then come back to it, like, three to four hours later, you- you're still getting the caching performance out of it. And launchedVibhu [00:34:04]: And you cut the cost there quite a bit too, right, with the new model?Nikunj Handa [00:34:07]: Oh, yeah. That's right.Vibhu [00:34:08]: Like, 25% cheaper, soNikunj Handa [00:34:08]: Yeah, with, like, driving down cache reads, yeah.Cache Pre-Warming and Cost-Efficient Agent ThreadsVibhu [00:34:10]: For builders, they should implementNikunj Handa [00:34:13]: YeahVibhu [00:34:13]: Because it's significantly cheaper.Nikunj Handa [00:34:14]: Yeah. Yeah. Just, like, building your apps with, like, to be very cache aware and sort of, like, use our prompt diagnostics or cache diagnostics tool to figure out, like, where things are dropping off. And, so the caching part is, like, really important. yeah, I also wanted to talk about pre-warming. We have that in the API now. So, like, if you know that, “Hey, I'm gonna get a cache,” like-- sorry, “I'm gonna get this prompt. I just wanna, like, pre-warm the cache, pay, like, the cache write fee right now, and then, like, have it sort of ready to go for the next 30 minutes for whenever.”Swyx [00:34:49]: And it can spawn many instances of that thread.Nikunj Handa [00:34:51]: Exactly, yeah.Swyx [00:34:52]: Yeah.Nikunj Handa [00:34:52]: You can just keep going and haveSwyx [00:34:54]: Yeah, just keep messing with the prompt thereNikunj Handa [00:34:55]: Tons and tons of that. and so, yeah, like, I'm very excited about getting feedback on, like, the low-level performance things that we can keep making Responses API the most performant and reliable way to, like, build on top of an LLM. And then you basically have our, like, new products where I'm just looking for, like, any and all feedback.Swyx [00:35:15]: Yeah, just use it, right?Nikunj Handa [00:35:16]: So yeah, just useSwyx [00:35:16]: Tell us what toNikunj Handa [00:35:17]: Yeah. Define our roadmap for us, please. So yeah.Swyx [00:35:20]: I think for me, the caching thing, great, right? Like, obviously very needed. But at the end of the day, you're still bumping up against a million-token contextCompaction and Managing Million-Token ContextsNikunj Handa [00:35:28]: Mm-hmmSwyx [00:35:28]: And that's probably not gonna change for the foreseeable future.Nikunj Handa [00:35:31]: Mm-hmm.Swyx [00:35:31]: Like, you still need good compression.Nikunj Handa [00:35:33]: Yeah.Swyx [00:35:33]: What is the best practice there?Nikunj Handa [00:35:34]: Yeah. Yeah, totally. so firstly, OpenAI has its own, like, proprietary compression, compSwyx [00:35:40]: Which is inNikunj Handa [00:35:41]: Compaction.Vibhu [00:35:42]: Compaction.Swyx [00:35:42]: It's in the agents.Vibhu [00:35:43]: It's in the API.Nikunj Handa [00:35:43]: Yes.Vibhu [00:35:43]: Agents API.Nikunj Handa [00:35:44]: Yeah.Swyx [00:35:44]: You decide for us, right?Nikunj Handa [00:35:45]: Yeah, exactly. So in the Agents API, it comes built into the harness. and if you're in Responses API, there's, like, two ways of doing it. One is what we call server-side compaction, which is you basically tell Responses API that if you ever hit this threshold of tokens, just auto-compact it and, like, go back, or sorry, like, reduce the context, being used. And the second way is, like, /compact, which is, like, if you want full control. So you can, like, /compact at any timeSwyx [00:36:15]: I hear youNikunj Handa [00:36:15]: Have your own logic on when to, likeSwyx [00:36:17]: It's not AGI.Nikunj Handa [00:36:18]: It.Swyx [00:36:18]: It's not AGI.Nikunj Handa [00:36:19]: Yeah. Yeah.Swyx [00:36:20]: Yeah. But it, I meanNikunj Handa [00:36:20]: YeahSwyx [00:36:20]: It is the manual override.Nikunj Handa [00:36:21]: Yeah, it is the manual way. And like, I don't know, but a lot of the big coding agents like to do it manually. I mean, like, if you look at the Codex implementation of it in the Code- open source Codex harness, you can see that they use /compact and do it. and, there's also, like, new, by the way, new compaction techniques that we are working on. Some of them you will be able to see in the Codex harness. Like, it's already implemented in the Codex harness. And so, they're like some file-based, systems that we are, like, experimenting with. So yeah, lots of cool stuff going on around in compaction as well.Swyx [00:36:57]: Cool. we are running out of time.Nikunj Handa [00:36:59]: Okay.Swyx [00:36:59]: I think you've talked about, a lot about performance and talked a lot about, the new APIs that you're launching. Can you give us any other hints as to things that you're interested in as far as the future of the platform is concerned?Higher-Level Platform Primitives and the AI CloudNikunj Handa [00:37:13]: We're obviously like very low level. Like, I used to work at Stripe before this, and, at Stripe a lot of the game was like building these higher level primitives and products on top of like the core payments primitives. and, I'm always like curious about what the best way of doing that is in AI. And I think we've had a couple of attempts at that. We like had launched assistance API like way back in the day, and like wasn't really the right fit. We were sort of like going off with this like Agents API, and, it gives you the codex harness, but like where's like the, what's the right amount of flexibility to give in that? That's like an open question. Like how should we like have memory walls and like all of these like higher level like API objects to take away, also like to abstract away more, like storage concepts. Like this is like a whole, like, there's a whole space that I'm like very curious about figuring out how we design. I think a lot of things in AI are just have a low-level API primitive and see an example harness and go and have your coding agent implement that. But how much of that do we build into the API is like a constant question that I'm thinking about.Swyx [00:38:24]: Yeah.Nikunj Handa [00:38:24]: So I don't know if folks have thoughts on that. If anyone has ideas, it would be super interesting to hear.Swyx [00:38:30]: Yeah. The analogy I always bring back to, and we'll end there, is, you're building an AI cloud, right?Nikunj Handa [00:38:35]: Mm-hmm.Swyx [00:38:35]: Like, which is, something that, Sam said a year agoNikunj Handa [00:38:38]: Mm-hmmSwyx [00:38:38]: Where, and you're, it's almost like you're kind of doing the AWS invention and you have to do, okay, this is EC2Nikunj Handa [00:38:45]: YeahSwyx [00:38:45]: And this is S3, and this is like. But you're doing the AI-native versions of each of these.Vibhu [00:38:48]: There are a lot of analogies, so you're pre-warming caches for stuff that you know will beNikunj Handa [00:38:53]: Yeah.Vibhu [00:38:53]: And it's nice that it's all exposed to buildersClosingNikunj Handa [00:38:56]: Mm-hmmVibhu [00:38:56]: ‘cause it just opens up ways that you can build new things.Nikunj Handa [00:38:59]: Yeah, absolutely.Swyx [00:39:00]: Okay.Vibhu [00:39:00]: Awesome. WellSwyx [00:39:01]: That's everything.Nikunj Handa [00:39:01]: Thank you, guys.Vibhu [00:39:02]: Thank you.Nikunj Handa [00:39:02]: Yeah. This is a public episode. If you'd like to discuss this with other subscribers or get access to bonus episodes, visit www.latent.space/subscribe

In the final hour of the show, Mac & Bone are joined by Willie P, who voices his frustrations with MLS officials after Charlotte FC's loss last week, they talk about their biggest conclusions from the world of college football, with the first month in the season, they preview the night in sports, they read funny texts, & more See omnystudio.com/listener for privacy information.

Mac & Bone start Wednesday's show, talking about the Braves winning Game 1 of their Wild Card series against the Phillies, & the Hurricanes losing their season opener, they react to more audio from a defensive Shane Beamer, & discuss the latest on the Panthers injury front See omnystudio.com/listener for privacy information.

In the second hour, Mac & Bone play audio from the world of college football, including Nick Saban, Urban Meyer, and Shane Beamer, former Panther Brentson Buckner joins the show, to talk about the adjustments the Panthers need to make after the Browns loss, before a Wednesday edition of Random Crap See omnystudio.com/listener for privacy information.

In the third hour, Mac & Bone turn their attention to the Lions game, on Sunday Night Football, as they discuss if this is shaping up to be a loss with all the injuries, Blain Crain joins the show, to talk about the upcoming weekend of college football, & they react to a fan survey's ranking of Panther fans See omnystudio.com/listener for privacy information.

On Homecoming the BGSU defense turned in a ferocious performance but the Falcons fell to USF, 14-6. We'll analyze that game and peek ahead to Saturday's MAC opener at Miami. Guests include: Coach Eddie George, QB Jay Kastantin, DL Kade Kostus and Saleh Brown, RB Austyn Dendy, John Gibson and "The Voice of the RedHawks", Steve Baker.See Privacy Policy at https://art19.com/privacy and California Privacy Notice at https://art19.com/privacy#do-not-sell-my-info.

Jared Sorge stops by to chat about Arborist, his native Mac command center for Git work trees. We get into running agents in parallel with work trees, when to drop from SwiftUI down to AppKit, and selling a Mac app outside the App Store with Sparkle, Stripe, and RevenueCat, and somehow end up talking about the iPhone Duo.GuestJared SorgeJared Sorge (@jsorge@mastodon.social) - Mastodonjsorge (Jared Sorge)Jared Sorge | LinkedInJared Sorge (@jsorge) • ThreadsArborist - A native macOS command center for Git repositories and worktreesTaphouse SoftwareRelated LinksArborist 1.2 - jsorge.netBaseplate - Track your LEGO collection - Taphouse Softwaregit-worktree Documentation - GitTower - Git clientNova - Panicmise - dev tools, env vars, task runnerjust - a handy way to save and run project-specific commandsswift-subprocess - GitHubSparkle - Software update framework for macOSRevenueCatManaged Payments - Stripe DocumentationSQLiteData - Point-Free - GitHubSharing - Point-Free - GitHubSwift Navigation - Point-Free - GitHubIntroducing Claude Design by Anthropic Labs - AnthropicMac-Assed Mac Apps - Daring FireballXcodeGen - GitHubShipaton 2026 - RevenueCatSwiftConiOSDevUKBushel - Mac virtualization for developersRelated EpisodesPractical Agents with Donny WalsEveryone Thinks They're Good at Prompting with Joe FabisevichThe Great SwiftUI Migration - Part 2 with Ben ScheirmanThe Great SwiftUI Migration - Part 1 with Ben ScheirmanmacOS Indie Deep Cuts with Aaron VeghMac Dev in 2021 with Daniel JalkutHow to Learn New APIs with Stewart Lynch - Part 1Automation Fun with Jared SorgeChapters(00:00) - Why Work Trees (06:56) - The Idea Behind Arborist (11:14) - SwiftUI vs. AppKit (17:05) - Picking the Right Tool for the Job (21:27) - From Problem to Product (25:30) - Shipping Outside the Mac App Store (29:59) - Licensing, Sandboxing & Subprocess (36:30) - Agentic Coding & the Product Engineer (45:17) - What's Next for Arborist WatchClick here to watch a video of this episode. TranscriptClick here to view the episode transcript. Support the Show ★ Support this podcast on Patreon ★ Thanks to our supporters: Thanks to our monthly supporters Steven Lipton Welcome new supporters: Social MediaLinkedIn - @leogdionGitHub - @brightdigitGitHub - @leogdionMastodon - @leogdion@c.imYouTube - @brightdigitX - @leogdionX - @brightdigitCreditsMusic from https://filmmusic.io "Blippy Trance" by Kevin MacLeod (https://incompetech.com) License: CC BY (http://creativecommons.org/licenses/by/4.0/)

Federico Viticci of MacStories joins the show this week! Federico shares his experience using Apple's new M5 Ultra Mac Studio & running local AI agents with the machine. John Ternus is looking to get the company to run faster & leaner. And AT&T may not support Apple's new iPhone Handoff feature? M5 Ultra Mac Studio Review: The dream Mac for local AI agents. Apple's new CEO seeks to make company run faster and leaner. AT&T seemingly has no plans to support Apple's new iPhone Handoff feature. iPhone 18 Pro Face ID rebooting bug to be fixed in iOS update. Meta announces VR headset for $1299. Picks of the Week Federico's Picks: Open Minis, Cadu Bot, and Comet KVM Andy's Pick: Keychron K3 v2 Christina's Picks: Xounds Redux & FruitMenu Redux Hosts: Leo Laporte, Andy Ihnatko, and Christina Warren Guest: Federico Viticci Download or subscribe to MacBreak Weekly at https://twit.tv/shows/macbreak-weekly. Join Club TWiT for Ad-Free Podcasts! Support what you love and get ad-free audio and video feeds, a members-only Discord, and exclusive content. Join today: https://twit.tv/clubtwit Sponsors: PaloAltoNetworks.com/Idira coveron.com/macbreakweekly and use code macbreakweekly cachefly.com/twit

We're ONE WEEK away from the launch ofThis Wasn't the Plan is out! In todays episode Mac and Kenz give us the inside scoop on the book, the parts that hit close to home. Then it's straight into real life: Mac is 38 weeks pregnant and navigating contractions after emergency surgery, while Kenz is juggling house projects, horse-girl dreams, and the general chaos of September. They also get honest about learning to accept help, slowing down, and making more room for joy—plus plenty of side quests along the way!! ⁠Preorder This Wasn't The Plan!⁠ Fill out the form HERE to get your preorder goodies! SEEDS: Download the Seed app and take one small step today: plant your first seed and see what God can grow! Learn more about your ad choices. Visit megaphone.fm/adchoices