Agents Hour

Mastra

The AI Agents show that discusses hot topics in the world of AI, talks with guests building AI agents and applications, and shows the actual code of how AI applications are being built today. Hosted by Shane Thomas and Abhi Aiyer from Mastra. Watch the livestream on Youtube and X on Monday at 12PM pacific time. Watch the video versions on Spotify or YouTube.

  1. 20h ago ·  Video

    Mastra Got Hacked. Here's What We Learned

    Mastra got hacked. In this special edition of Security Corner, Shane Thomas and Abhi Aiyer break down exactly what happened when a supply chain attack hit Mastra's npm packages — an attack that appears to trace back to hackers in North Korea. They're joined by Ismail Pelaseyed, co-founder and CTO of Superagent, for the outside view on how these campaigns actually work. You'll hear how a single, ordinary-looking call turned into a full npm account takeover, the small oversight that turned a scare into a genuine crisis, and why a malicious package was still live on the registry weeks after it was reported. Ismail makes the case that getting hacked is a side effect of success — and that the real problem runs deeper than any one team. You'll learn why he thinks npm and PyPI have dropped the ball on security, how AI now lets attackers one-shot a convincing phishing app, and what every maintainer should be doing to harden their pipeline before a trusted contributor becomes the way in. It's the unfiltered version, told by the people who lived through it. Connect with Ismail Pelaseyed: https://x.com/pelaseyed https://superagent.sh Connect with the hosts: https://x.com/smthomas3 https://x.com/abhiaiyer 📚 MASTRA RESOURCES https://mastra.ai https://x.com/mastra_ai https://mastra.ai/community/discord https://github.com/mastra-ai https://mastra.ai/course https://mastra.ai/books/principles-of-building-ai-agents https://mastra.ai/books/patterns-of-building-ai-agents Mastra is an open-source TypeScript framework designed for building and shipping AI-powered applications and agents with minimal friction. It supports the full lifecycle of agent development — from prototype to production. CHAPTERS 0:00 Intro: a special Security Corner 0:55 The supply chain attack on Mastra 1:29 How they got in: a fake Teams call 2:27 The npm account takeover 3:54 EasyDjS and the scramble to fix it 5:49 Why success makes you a target 9:20 How AI supercharges phishing 9:59 Hardening against compromised contributors 11:10 Open source under strain: IBM's $5B bet 12:27 npm and PyPI keep dropping the ball 14:31 Inside the fake package, and how Socket caught it 16:20 The fear-selling problem in security 18:02 Superagent!

    19 min

  2. 1d ago ·  Video

    GPT-5.5 Beats Fable, Cursor Takes On GitHub & Midjourney Scans Your Body | This Week in AI

    Fable is gone, and the race to replace it is already on. Shane and Abhi open with the fallout — reports that Mythos breached classified NSA systems, the ID-verification future that may follow, and David Sacks' "you asked for it" take. Then the story flips: OpenAI's GPT-5.5 Cyber lands state-of-the-art on Cyber Gym, beating Fable and Mythos on the underlying benchmarks, with OpenAI Daybreak shipping alongside it. GPT-5.6 leaks, then slips to mid-July. GLM 5.2 arrives near Opus 4.8, tops Design Arena, and runs on a Mac. Cursor goes after GitHub with Origin, adds mobile and its own frontier model on Colossus after the SpaceX deal closes. Vercel ships Eve, Fred Schott counters with Flue, Claude lands in Slack, and Midjourney — yes, the image company — unveils a full-body medical scanner headed for spas. AI Agents Hour is a weekly livestream by Mastra CPO Shane Thomas and CTO Abhi Aiyer. Mondays 12PM Pacific. 📚 READ MORE The Fable story, Mythos & the NSA: https://x.com/kimmonismus/status/2068605229965234238 GPT-5.5 Cyber beats Fable (Sam Altman): https://x.com/sama/status/2069121360744550796 OpenAI Daybreak: https://x.com/OpenAI/status/2069104283824640023 GPT-5.6 leak (Mark K): https://x.com/mark_k/status/2069169916432003105 GPT-5.6 delayed: https://x.com/synthwavedd/status/2069432791184650426 GLM 5.2 (Z.ai): https://x.com/zai_org/status/2066938937344495629 GLM 5.2 tops Design Arena: https://x.com/Designarena/status/2066940737011560652 GLM 5.2 vs Opus (Cline): https://x.com/cline/status/2069171146994729078 1-bit GLM 5.2 runs local (Unsloth): https://x.com/UnslothAI/status/2069418532375564484 Cursor Origin: https://x.com/cursor_ai/status/2069149296436330776 Cursor Compile keynote: https://x.com/cursor_ai/status/2067012220832329782 Swyx on Origin: https://x.com/swyx/status/2066928345246470204 Vercel Eve: https://x.com/vercel/status/2067180054979936413 Flue 1.0 (Fred Schott): https://x.com/FredKSchott/status/2066962296119959581 Codex record-replay to skills: https://x.com/OpenAIDevs/status/2067681320281723113 Claude Tag in Slack: https://x.com/claudeai/status/2069468693017268244 Replit in Slack: https://x.com/Replit/status/2067661213278900402 Midjourney Medical: https://x.com/midjourney/status/2067421950314688759 Sakana Fugu: https://x.com/SakanaAILabs/status/2068861630327443966 📚 MASTRA RESOURCES Mastra: https://mastra.ai Mastra on X: https://x.com/mastra_ai Mastra Discord: https://mastra.ai/community/discord Mastra GitHub: https://github.com/mastra-ai Principles of Building AI Agents (Book): https://mastra.ai/books/principles-of-building-ai-agents Patterns for Building AI Agents (New Book): https://mastra.ai/books/patterns-of-building-ai-agents WHAT IS MASTRA? Mastra is an open-source TypeScript framework designed for building and shipping AI-powered applications and agents with minimal friction. It supports the full lifecycle of agent development—from prototype to production. You can integrate it with frontend and backend stacks (e.g., React, Next.js, Node) or run agents as standalone services. If you're a JavaScript or TypeScript developer looking to build an agentic or AI-powered product without starting from first principles, Mastra provides the scaffolding, tools, and integrations to accelerate that process. ⏱️ CHAPTERS 00:00 Cold open 00:30 Welcome 01:02 Fable fallout: did Mythos breach the NSA? 03:10 GPT-5.5 Cyber beats Fable & OpenAI Daybreak 05:23 GPT-5.6 delayed, Gemini 3.5 Pro slips 05:52 GLM 5.2: near-Opus, and it runs on a Mac 09:52 Subscribe break 09:55 Cursor's Origin takes on GitHub 11:12 Cursor mobile, frontier model & the SpaceX deal 11:52 Vercel's Eve, Flue & Codex skills 13:48 Claude Tag & Replit in Slack 14:57 Midjourney goes medical: full-body scanners 16:42 Sakana Fugu & the rise of model routing 19:37 Outro

    20 min

  3. 2d ago ·  Video

    How AI Broke Open Source Security | Security Corner with Ismail Pelaseyed

    Open source is under attack, and AI changed the math. In this Security Corner, Ismail Pelaseyed, co-founder and CTO of Superagent, joins Shane and Abhi to break down how the software supply chain became the soft underbelly of everything we build. An attack that once took an army of researchers and weeks of work now takes about an hour, and the attacker no longer needs a frontier model to pull it off. Ismail traces how most breaches begin, why phishing has become almost impossible to spot, and how a single poisoned dependency can cascade across an entire ecosystem. You'll get concrete steps any maintainer or developer can take today: switching package managers, enabling the security scanners that ship for free, and standing up an adversarial agent that hunts for chained exploits before an attacker finds them. Ismail also warns that the same instincts protecting enterprises may be quietly strangling open source itself. You'll hear why he thinks the big registries have dropped the ball, what a "Darwinian GitHub" would mean for anyone shipping a new package, and the one move he believes can keep the ecosystem alive. Superagent: https://superagent.sh Superagent on X: https://x.com/superagent_ai Superagent on GitHub: https://github.com/superagent-ai pnpm: https://pnpm.io Socket: https://socket.dev 📚 MASTRA RESOURCES Mastra: https://mastra.ai Mastra on X: https://x.com/mastra_ai Discord: https://mastra.ai/community/discord GitHub: https://github.com/mastra-ai Free course: https://mastra.ai/course Principles of Building AI Agents: https://mastra.ai/books/principles-of-building-ai-agents Patterns of Building AI Agents: https://mastra.ai/books/patterns-of-building-ai-agents WHAT IS MASTRA Mastra is an open-source TypeScript framework designed for building and shipping AI-powered applications and agents with minimal friction. It supports the full lifecycle of agent development — from prototype to production. ⏱️ CHAPTERS 0:00 Cold open 0:21 What is Superagent 0:53 How AI sped up attack timelines 2:14 Why phishing is the way in 4:35 Outdated CI/CD workflows 6:04 Two defenses: CI/CD checks and switching to pnpm 7:18 The risk hiding in skills and agents 8:11 Should you delay installing new packages? 8:54 The Darwinian GitHub threat to open source 9:55 Why supply chain attacks are so popular 11:34 Will companies abandon open source? 13:53 Why Ismail is frustrated with GitHub and npm 14:32 Practical defenses for maintainers 18:12 Where to find Superagent

    19 min

  4. Jun 18 ·  Video

    Claude Fable 5: Launched, Hyped, Banned by the Government | This Week In AI

    Fable came and went in a week. Shane and Abhi break down the strangest model launch yet — Claude Fable 5, a Mythos-class model Anthropic said was too capable to release widely, until a US export-control directive made it vanish for everyone. We cover the whole arc: the launch hype, the pricing that had people spending $1,000 a day, the silent fallbacks to Opus, the system-prompt leak, and the snitch that triggered a 90-minute shutdown. Then a stacked back half — China's open-weight surge, OpenRouter Fusion, loop engineering vs loopcraft, the agent-learning gold rush, OpenAI filing to go public, and Dario's new essay. AI Agents Hour is a weekly livestream by Mastra CPO Shane Thomas and CTO Abhi Aiyer. Mondays 12PM Pacific. 📚 READ MORE Claude Fable 5 launch: https://x.com/claudeai/status/2064394146916229443 Pokémon beaten with vision: https://x.com/Baconbrix/status/2064418858073784530 Export-control announcement: https://x.com/anthropicai/status/2065597531644743999 Amazon/WSJ report (Theo): https://x.com/theo/status/2065665304882209132 David Sacks on the ban: https://x.com/davidsacks/status/2065853007619588171 Token capital (Satya Nadella): https://x.com/satyanadella/status/2066182223213293753 Siri as a harness (Weinbach): https://x.com/mweinbach/status/2065630219021492474 MiniMax M3 open weights: https://x.com/minimax_ai/status/2065436935188058208 GLM 5.2: https://x.com/zai_org/status/2065704919299235870 Kimi K2 Code High Speed: https://x.com/kimi_moonshot/status/2066467110960959833 Cohere North Mini Code: https://x.com/cohere/status/2064378058329526556 Gemma 4 on consumer hardware: https://x.com/unslothai/status/2065433326706684135 Diffusion Gemma: https://x.com/unslothai/status/2065107734916432189 OpenRouter Fusion API: https://x.com/openrouter/status/2065856853989270011 AI SDK harnesses (Vercel): https://x.com/vercel_dev/status/2065509970775519569 Swyx on loopcraft: https://x.com/swyx/status/2065307558198567206 OpenEnv joins Hugging Face: https://x.com/ben_burtenshaw/status/2063991191415267492 Adaline 2.0 / agent learning: https://x.com/adiix_official/status/2066172819952566643 Cognition Frontier Code: https://x.com/cognition/status/2064061031912288715 Ramp SWE-bench: https://x.com/RampLabs/status/2065485806605619304 AWS on AI-generated code: https://x.com/awscloud/status/2064449711155589396 OpenAI files to go public: https://x.com/OpenAINewsroom/status/2065088002335158753 OpenAI acquires Ona: https://x.com/OpenAINewsroom/status/2064094175541461220 Salesforce acquires Fin AI: https://x.com/fin_ai/status/2066493998852686074 Mistral in talks to raise: https://x.com/business/status/2065420995393941692 Dario's essay on the AI exponential: https://x.com/DarioAmodei/status/2064781775247950326 📚 MASTRA RESOURCES Mastra: https://mastra.ai Mastra on X: https://x.com/mastra_ai Mastra Discord: https://mastra.ai/community/discord Mastra GitHub: https://github.com/mastra-ai Learn Mastra in the world's first MCP-Based Course: https://mastra.ai/course Principles of Building AI Agents (Book): https://mastra.ai/books/principles-of-building-ai-agents Patterns for Building AI Agents (New Book): https://mastra.ai/books/patterns-of-building-ai-agents WHAT IS MASTRA? Mastra is an open-source TypeScript framework designed for building and shipping AI-powered applications and agents with minimal friction. It supports the full lifecycle of agent development—from prototype to production. You can integrate it with frontend and backend stacks (e.g., React, Next.js, Node) or run agents as standalone services. If you're a JavaScript or TypeScript developer looking to build an agentic or AI-powered product without starting from first principles, Mastra provides the scaffolding, tools, and integrations to accelerate that process. ⏱️ CHAPTERS 00:00 Cold open & welcome 00:40 Claude Fable 5: the launch and the hype 01:53 The price problem and silent Opus fallbacks 06:42 Our experience + the system-prompt leak 08:51 The 90-minute export-control shutdown 12:40 Microsoft's "token capital" & where Fable goes 17:07 Apple at WWDC: Siri as a harness 17:57 China's open models: MiniMax M3, GLM 5.2, Kimi K2 21:11 Local-first: Cohere, AMD, Diffusion Gemma 24:58 OpenRouter Fusion & AI SDK harnesses 27:07 Loop engineering, loopcraft & OpenEnv 29:09 Agent learning & new coding benchmarks 32:14 AWS, the snitch & OpenAI's IPO 33:37 Salesforce, Mistral & Le Chaton Fat 36:42 Quick hits & a Fable eulogy

    38 min

  5. Jun 11 ·  Video

    Loop Engineering, OpenAI Sites & the Great China Model Shift | This Week In AI

    Shane and Abhi are in person this week — live from the CodeRabbit office — for a packed AI news rundown. The big theme: loop engineering. Boris Cherny (head of Claude Code) and Peter Steinberger both landed the same take within days — stop prompting your agents, start designing the loops that prompt them. We walk the whole evolution: the traditional loop, the Ralph loop, /goal, and Claude Code's new dynamic workflows — and debate whether "stop prompting" is real insight or just clickbait. Plus: Anthropic engineers shipping 8x more code (and the "depressed employees" reply), agentic traffic passing human traffic on the web for the first time, OpenAI's Codex Sites taking aim at Lovable, Cognition's $10M AI Productivity Guarantee and Devin Desktop, Cloudflare acquiring VoidZero, the accelerating shift to Chinese models (Lindy going 100% DeepSeek), Notion disabling Anthropic models over reliability, a big open-model dump (Gemma 4, Magenta RealTime 2, Miso One, Nemotron, Liquid, GLM 5.1, MiniMax M3), funding rounds (Suno, Supabase), Brian Chesky's new AI lab, and whether AI is actually profitable yet. Recorded live at the CodeRabbit office — thanks to the CodeRabbit team. AI Agents Hour is a weekly livestream by Mastra CPO Shane Thomas and CTO Abhi Aiyer. Mondays 12PM Pacific. 📚 READ MORE Anthropic ships 8x more code: https://x.com/AnthropicAI/status/2062568864240836995 "Depressed employees" reply: https://x.com/jasonbotterill/status/2062579899412713605 Bots pass humans (Matthew Prince): https://x.com/eastdakota/status/2062212701414187452 Boris Cherny on loops (via @rohanpaul_ai): https://x.com/rohanpaul_ai/status/2063289804708835412 Steipete — design loops, don't prompt: https://x.com/steipete/status/2063697162748260627 OpenAI Codex Sites: https://x.com/openai/status/2061845949170045346 Cognition AI Productivity Guarantee: https://x.com/cognition/status/2062597242167628019 Devin Desktop: https://x.com/cognition/status/2061889596703551926 Cloudflare acquires VoidZero: https://x.com/voidzerodev/status/2062520542121304146 Shift to Chinese models (Nick Thompson): https://x.com/nxthompson/status/2063712713654628549 Lindy → DeepSeek V4 (Flo Crivello): https://x.com/altimor/status/2062389885437366342 Notion disables Anthropic models: https://x.com/notionstatus/status/2063477745796161904 Gemma 4 12B: https://x.com/Google/status/2062203526588088452 Gemma 4 QAT (Unsloth): https://x.com/UnslothAI/status/2062931482746994755 Magenta RealTime 2: https://x.com/googlegemma/status/2062619217967628693 Miso One: https://x.com/aodenteomt/status/2062204362102100295 Nemotron-3.5-ASR-Streaming: https://x.com/piotrzelasko/status/2062538923776290909 Liquid LFM2.5-VL-Extract: https://x.com/liquidai/status/2062686748291846307 Baseten — GLM 5.1 at 160+ TPS: https://x.com/baseten/status/2062942929883426860 MiniMax M3 faster: https://x.com/ryanleeminimax/status/2061982791458521116 MiniMax M3 × Fireworks: https://x.com/FireworksAI_HQ/status/2062187803476111405 Brian Chesky's AI lab: https://x.com/shiringhaffary/status/2062618738881675579 Is AI profitable?: https://isaiprofitable.com/ v0 × Shopify: https://x.com/v0/status/2062859311869497355 Factory Router: https://x.com/factoryai/status/2061862733126275549 Hermes Desktop (Nous): https://x.com/NousResearch/status/2061843507417944552 ⏱️ CHAPTERS 00:00 Cold open 00:36 Welcome — live from the CodeRabbit office 00:56 Anthropic ships 8x more code (and the "depressed employees" reply) 02:46 Bots pass humans: agentic traffic overtakes the web 03:17 Loop engineering: stop prompting, start designing loops 10:53 Subscribe break 11:03 OpenAI Codex Sites — is Lovable cooked? 11:56 Cognition's $10M AI Productivity Guarantee 13:21 Devin Desktop (pour one out for Windsurf) 14:03 Cloudflare acquires VoidZero 14:16 The China shift: DeepSeek, Qwen, GLM, MiniMax 15:39 Notion disables Anthropic models 16:12 Model dump: Gemma 4, Magenta RT2, Miso One, Nemotron, Liquid, GLM 5.1, MiniMax M3 19:26 Funding & M&A: Suno, Supabase, SpaceX, Chesky's AI lab 21:00 Is AI profitable? 21:35 Quick hits: v0 × Shopify, Factory Router, Hermes Desktop 22:45 Outro & thanks to CodeRabbit

    24 min

  6. Jun 8 ·  Video

    Inside an AI-Native Company | Michael Grinich, WorkOS

    WorkOS quietly powers the auth and enterprise layer under OpenAI, Anthropic, Cursor, and a long list of companies building the AI era. So when its founder decides his entire company should learn to code, it's worth asking why. Michael Grinich joins Shane and Abhi to talk about what "AI-native" actually looks like from the inside — the in-house coding agent his team built instead of buying, the all-day internal hackathons, and the operating principle he now hires for: everybody codes. He shares how AI is reshaping go-to-market and not just engineering, why he braced for pushback and got the opposite, and the one trait that separates the people who thrive from the people who stall. We close on the thinking behind his Death of UI talk, and where human-computer interaction goes from here. 🔗 MICHAEL The Death Of UI https://youtu.be/azoM7uz8Jhs Michael Grinich on X — https://x.com/grinich WorkOS — https://workos.com 📚 MASTRA RESOURCES https://mastra.ai https://x.com/mastra_ai https://mastra.ai/community/discord https://github.com/mastra-ai https://mastra.ai/course https://mastra.ai/books/principles-of-building-ai-agents https://mastra.ai/books/patterns-of-building-ai-agents WHAT IS MASTRA? Mastra is an open-source TypeScript framework designed for building and shipping AI-powered applications and agents with minimal friction. It supports the full lifecycle of agent development — from prototype to production. CHAPTERS 0:00 "Everybody codes" 0:13 What WorkOS actually does 1:33 Inside the Applied AI showcase 2:39 Horizon, the in-house coding agent 3:49 Build it or buy it 5:50 WorkOS's marketing strategy 7:29 Getting everyone building 9:40 "We haven't found our limits yet" 11:41 You have agency to learn 13:38 Should every company build this? 16:04 The Death of UI 17:58 Where to find Michael

    19 min

  7. Jun 4 ·  Video

    Opus 4.8, Anthropic's S-1, MiniMax M3 & NVIDIA Pays You to Host a Data Center | This Week In AI

    Anthropic filed to go public. The S-1 lands the same week as a $65 billion Series H at a $965 billion valuation, a claimed first profitable quarter, and a home listing that takes Anthropic stock as payment. Opus 4.8 shipped mid-week, and Shane and Abhi give the vibe check: a polish pass over 4.7 more than a step change, still trailing GPT-5.5 on DeepSWE, with GPT-5.6 spotted in Codex logs. The quieter, more interesting release: mid-conversation system messages, steering a model mid-task without breaking the prompt cache. MiniMax M3 is out, agent-tuned and long-context at a fraction of frontier pricing. NVIDIA used Computex to push AI onto the desktop with Vera, RTX Spark, and a Windows DGX Station that runs trillion-parameter models locally, plus a startup unit that bolts onto your house and pays you for compute. OpenAI brings Codex to Windows and ships private MCP servers. Claude Code's dynamic workflows get cloned by pi within a day, Devin raises $1B, and the model-vs-harness debate heats up. Plus continual learning as the next wave, a $500M accidental Claude bill, Corgi's seven-days-a-week firestorm, and a GitHub Star Party pick. 🔗 LINKS Pope on AI: https://x.com/pontifex/status/2060322763718725798 Kuzma on TBPN: https://x.com/tbpn/status/2060374399031632176 Opus 4.8: https://x.com/alexalbert__/status/2060043196655362358 Mid-conversation system messages: https://x.com/swyx/status/2060044644193624253 Opus 4.8 on DeepSWE: https://x.com/arrakis_ai/status/2060757773579956640 GPT-5.6 sighting: https://x.com/hqmank/status/2060334752369160472 Anthropic S-1: https://x.com/AnthropicAI/status/2061478052257841495 Series H: https://x.com/anthropicai/status/2060061347522433422 First profitable quarter: https://techcrunch.com/2026/05/20/anthropic-says-its-about-to-have-its-first-profitable-quarter/ $500M Claude bill: https://x.com/Polymarket/status/2060034216906068131 Zillow listing: https://x.com/Yuchenj_UW/status/2060776120380010932 Mythos class model: https://x.com/kimmonismus/status/2060047510853312557 MiniMax M3: https://x.com/minimax_ai/status/2061266317815296322 Computex in 12 minutes: https://youtu.be/ugNnw4lAMWA NVIDIA Vera: https://x.com/nvidianewsroom/status/2061298380022726734 RTX Spark: https://x.com/nvidia/status/2061313474005737829 DGX Station for Windows: https://x.com/nvidianewsroom/status/2061307670607319201 Home AI data center: https://x.com/w1nklerr/status/2060091525413884408 Codex on Windows: https://x.com/OpenAI/status/2060428604727771421 Private MCP servers: https://x.com/openaidevs/status/2059703536825565499 Dynamic workflows: https://x.com/claudedevs/status/2060044853279617150 pi dynamic workflows: https://x.com/micLivs/status/2060115468531499224 Devin raises $1B: https://x.com/cognition/status/2059660758531940856 grok-build: https://x.com/xai/status/2060392249402552457 Codex as QA: https://x.com/steipete/status/2061208638027395490 Cua on Windows: https://x.com/trycua/status/2059688960838828391 Elad Gil on liftoff: https://x.com/eladgil/status/2061129428084887593 Continual learning pivot: https://x.com/swyx/status/2061206120233054327 Trajectory: https://trajectory.ai/ Motion Studio: https://x.com/_adishj/status/2059666916835463646 Koji AI tutor: https://x.com/suekhim/status/2060378988606878147 Asana acquires Stack AI: https://x.com/techcrunch/status/2060091143556395421 Corgi raises $106M: https://x.com/nico_laqua/status/2060028908704243782 Coral board with Gemma: https://x.com/googlegemma/status/2059740184930074758 Cloudflare web search: https://x.com/cherryjimbo/status/2060717359979958513 Voice-controlled computer: https://x.com/farzatv/status/2060865350036750847 rift: https://github.com/anomalyco/rift 📚 MASTRA RESOURCES https://mastra.ai https://x.com/mastra_ai https://mastra.ai/community/discord https://github.com/mastra-ai https://mastra.ai/course https://mastra.ai/books/principles-of-building-ai-agents https://mastra.ai/books/patterns-of-building-ai-agents Mastra is an open-source TypeScript framework designed for building and shipping AI-powered applications and agents with minimal friction. It supports the full lifecycle of agent development — from prototype to production. 0:00 Cold open 0:29 Welcome + last week's callbacks 2:22 Opus 4.8 5:51 Anthropic files to go public 11:33 MiniMax M3 15:23 NVIDIA at Computex 18:11 NVIDIA's home AI data center 20:32 OpenAI ships for Windows 21:15 More coding agent news 25:07 Continual learning 27:42 Quick hits 34:04 GitHub Star Party

    36 min

  8. May 29 ·  Video

    Karpathy Joins Anthropic, China Ships Another Price Cut, Anthropic's SpaceX Bill - This Week In AI

    Shane and Abhi are back with AI news!  Andrej Karpathy joined Anthropic. The OpenAI co-founder and former Tesla AI head said he wants to "get back to R&D" at the LLM frontier. Same week, Greg Brockman posted "the model alone is no longer the product." Elon Musk announced SpaceX is offering AI compute as a service at significant scale, with Anthropic as the flagship customer. Tom Brown confirmed Anthropic is scaling on GB200 capacity in Colossus 2 through June. Anthropic is reportedly paying SpaceX $1.25B a month — a $15B run rate to one vendor. OpenAI offered $2M in tokens to every YC startup in the current batch in exchange for equity. WorkOS launched auth.md, an open protocol for agents to register for services on the web, with Cloudflare and Firecrawl as launch partners. The Chinese labs kept pushing. DeepSeek made their 75% discount permanent on V4-Pro. The architecture behind the price: V4's KV cache is 100x smaller, ~3GB VRAM for 1M tokens. Qwen shipped 3.7-Max. MiniMax teased a similar move. Anthropic shipped self-hosted sandboxes and MCP tunnels for Managed Agents, /workflows in Claude Code that replaces the LLM orchestrator with code, /usage for per-component token attribution, and a first-party security plugin. Google had a week. Gemini 3.5 Flash launched at 3x input and 6x output the price of 3 Flash — Theo's math shows it costs 2x more to run than 3.1 Pro on similar tasks. Gemini Omni lost a side-by-side to Seedance 2.0. Jack Wotherspoon shipped Antigravity CLI, Philipp Schmid debuted Managed Agents in the Gemini API, and Google open-sourced Agent Executor. Cursor shipped Composer 2.5 and published CursorBench. Datacurve released DeepSWE as a harder agentic coding benchmark. Supply-chain attacks kept rolling: Mini Shai-Hulud hit antv, TrapDoor crypto stealers spread across npm/PyPI/Crates.io, Megalodon injected 5,718 commits into 5,561 GitHub repos in six hours, and GitHub itself disclosed unauthorized access to its internal repositories. Cloudflare published their experience running Anthropic's Mythos against 50 of their own repos. The MCP 2026-07-28 RC is stateless. ElevenLabs launched Music v2 and Speech Engine. Runway shipped Aleph 2.0. Accenture laid off 11,000 in an $865M AI restructuring. Exa raised $250M at $2.2B. OpenRouter raised $113M. 🔗 LINKS https://x.com/karpathy/status/2056753169888334312 https://x.com/gdb/status/2057670776803996110 https://x.com/sama/status/2056933166875857290 https://x.com/grinich/status/2057884407135187292 https://x.com/deepseek_ai/status/2057854261699195173 https://x.com/teortaxestex/status/2057728159479443927 https://x.com/elonmusk/status/2057228707606196434 https://x.com/pitdesi/status/2057207627567014014 https://x.com/serenaa_ge/status/2059308218564890875 https://cursor.com/evals https://x.com/claudeai/status/2056645485696315581 https://x.com/theo/status/2056877869780107762 https://x.com/JackWoth98/status/2056805210761077059 https://x.com/_philschmid/status/2056836567470362955 https://x.com/cursor_ai/status/2056415413077233983 https://x.com/cloudflare/status/2056360412510060748 https://x.com/dsp_/status/2057780712187580924 https://x.com/elevenlabs/status/2059312414198235642 https://x.com/runwayml/status/2057530497597600169 https://x.com/exaailabs/status/2057132080317042697 https://x.com/openrouter/status/2059277623629664758 📚 MASTRA RESOURCES https://mastra.ai https://x.com/mastra_ai https://mastra.ai/community/discord https://github.com/mastra-ai https://mastra.ai/course https://mastra.ai/books/principles-of-building-ai-agents https://mastra.ai/books/patterns-of-building-ai-agents WHAT IS MASTRA? Mastra is an open-source TypeScript framework designed for building and shipping AI-powered applications and agents with minimal friction. It supports the full lifecycle of agent development — from prototype to production. 00:00 — Intro 00:58 — The unlikely AI cast: Pope, Kuzma, Karpathy, Brockman 05:36 — OpenAI offers $2M tokens to every YC startup 06:40 — auth.md from WorkOS 07:44 — China keeps shipping: DeepSeek, Qwen, MiniMax 09:24 — Anthropic + SpaceX: $1.25B a month 10:55 — Coding benchmarks: DeepSWE & CursorBench 13:29 — Anthropic ships: sandboxes, /workflows, /usage, security 15:08 — Google's week: Gemini 3.5 Flash, Antigravity, Managed Agents 18:36 — Cursor Composer 2.5 19:03 — The supply-chain attack marathon 22:31 — MCP 2026-07-28 RC goes stateless 23:02 — Voice, music, video: ElevenLabs & Runway Aleph 2.0 24:52 — Accenture layoffs, Exa $250M, OpenRouter $113M 26:24 — Quick hits

    34 min
See All (69)

About

The AI Agents show that discusses hot topics in the world of AI, talks with guests building AI agents and applications, and shows the actual code of how AI applications are being built today. Hosted by Shane Thomas and Abhi Aiyer from Mastra. Watch the livestream on Youtube and X on Monday at 12PM pacific time. Watch the video versions on Spotify or YouTube.

Information

  • Creator
    Mastra
  • Years Active
    2025 - 2026
  • Episodes
    69
  • Rating
    Explicit
  • Copyright
    © Copyright 2025 All rights reserved.
  • Show Website
    Agents Hour

You Might Also Like