Agents Hour

The 0x-alpha Mystery, Qwen's 27B Beats Opus 4.8 & Legal Is AI's Breakout Video

Agents Hour

Show Notes

A shorter but juicy one. Shane and Abhi open on the debate everyone's having — do you want to use your agent to reach into someone else's tool, or do you want that tool to build the best agent and meet you where you already are? Then the week's biggest mystery: a stealth model called 0x-alpha that appeared on OpenRouter beating Fable and Sol on coding, with a wild one-hundred-trillion-tokens-a-day capacity that had everyone convinced it was a secret Google model — until someone made the server name itself, and it turned out to be Z.ai. From there: Qwen breaks the size curve with a 27B model that outranks Opus 4.8 on the agentic index and runs on your own hardware, open-weight tokens cross 62% on Vercel's AI gateway, and Salesforce ships Slack Code so humans and agents can work in the same channel. Plus the case that legal is AI's breakout use case — Harvey trained its own model, Tenet, on a Kimi K3 base, and legal is the fastest-growing Codex adopter, up 108x since February. In the quick hits: agents now burn 5x the tokens humans do, and Tobi Lütke vibe-codes a Git-at-scale binary over a weekend. AI Agents Hour is a weekly livestream by Mastra CPO Shane Thomas and CTO Abhi Aiyer. Mondays 12PM Pacific. 📚 READ MOREWhose agent wins? (Ali Spittel): https://x.com/ASpittel/status/2090889137062826240The 0x-alpha situation: https://x.com/mtslive/status/2090872472174522701100 trillion tokens a day: https://x.com/brandonjcarl/status/2090798277625041157The DeepSWE benchmarks: https://x.com/kimmonismus/status/2090718270202528215The reveal — it's Z.ai: https://x.com/chetaslua/status/2091086141764354364Qwen's 27B beats Opus 4.8: https://x.com/ggerganov/status/208940988185808910262% open weights on Vercel: https://x.com/rauchg/status/2091234105702887879Slack Code (Benioff): https://x.com/benioff/status/2090240159115853956Harvey's Tenet model: https://x.com/harvey/status/2090454750059958440Codex adopters, legal up 108x: https://x.com/a16z/status/2091623289869508979Agents burn 5x the tokens: https://x.com/a16z/status/2091200032162857328Tobi's weekend Git binary: https://x.com/tobi/status/2091678506992222258 📚 MASTRA RESOURCESMastra: https://mastra.aiMastra on X: https://x.com/mastra_aiMastra Discord: https://mastra.ai/community/discordMastra GitHub: https://github.com/mastra-aiLearn Mastra: https://mastra.ai/learnPrinciples of Building AI Agents (Book): https://mastra.ai/books/principles-of-building-ai-agentsPatterns 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. ⏱️ CHAPTERS00:00 Cold open: whose agent wins?00:25 Welcome00:39 Your agent vs. their agent04:21 The 0x-alpha mystery05:01 The conspiracy theories06:01 The reveal: it's Z.ai (GLM)08:44 Qwen breaks the size curve09:50 Subscribe09:59 Open weights take the gateway (62% on Vercel)11:12 Slack Code: humans + agents, same channel13:35 Legal breaks out: Harvey's Tenet model16:58 Codex adopters: legal up 108x18:29 Quick hits: agents burn 5x the tokens19:53 Cursor Origin: Git at Any Scale22:32 Tobi's weekend Git binary23:30 Outro

More from Agents Hour

Oct 20, 2026

Brad Leford has been building software for 20 years and now spends most of his time helping small businesses figure out AI. His new side project, Plum, is a video calling app built for teams and AI agents. Any agent from any harness can join a Plum meeting through a link, using WebMCP to learn what it can do: listen, raise its hand, talk, and share assets. In the demo, Mastra agents keep the meeting on track while a Grok Bot session builds slides on request. Recordings and transcripts stay on your own disk instead of a vendor's cloud. Brad, Shane, and Abhi also talk about whether software is actually easy now, why the Mastra team decided it had AI psychosis, and what happens when agents and humans share context in the same room. And Brad shares the moment that pushed him to ship: Grok Bot taught Claude how to share an image, live in the meeting. Recorded live on AI Agents Hour, a weekly livestream by Mastra CPO Shane Thomas and CTO Abhi Aiyer. Mondays 12PM Pacific. 👤 ABOUT BRADBrad is a software engineer and consultant who has spent the better part of 20 years building apps and websites, including stints at Gatsby and Amazon. He now helps small and medium businesses, many in agriculture and small manufacturing, adopt AI and build the tools they need. Plum: https://useplum.app 📚 MASTRA RESOURCESMastra: https://mastra.aiMastra on X: https://x.com/mastra_aiMastra Discord: https://mastra.ai/community/discordMastra GitHub: https://github.com/mastra-aiLearn Mastra: https://mastra.ai/learnPrinciples of Building AI Agents (Book): https://mastra.ai/books/principles-of-building-ai-agentsPatterns 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. ⏱️ CHAPTERS00:00 Cold open00:17 Meet Brad02:09 Is software actually easy now?04:22 Spreadsheets to space shuttles05:06 Are small businesses AI-pilled?06:51 Why Brad built Plum08:01 Demo: agents in a meeting09:12 Any agent can join with WebMCP11:12 Agents as meeting participants12:07 Your meeting history, stored locally12:48 Working with agents in real time14:42 Shared context that doesn't reset15:41 Can agents speak in the meeting?16:32 When Grok Bot taught Claude17:37 Fun and serious use cases19:07 Bring your own agent19:22 How to try Plum

Oct 16, 2026

OpenAI found a recording device hidden in one of its offices and traced it back to an employee. Meanwhile the model releases kept coming: Mistral Large 4 aka Le Chonk, Claude Haiku 5.5, Meta's Muse Wonder and Gemini 4 Argon, which is finally available to everyone. OpenAI also dropped a pile of AI-solved math problems in a single day, and decision models are on round three with Jev's $870M Series A, SubQ Snap, Microsoft-Decision-1 and Clef-omni. Anthropic built its own source control to keep up with 30,000 code changes a day, updated its usage policy to ban abusing Claude, and reportedly lobbied the Pope on machine consciousness. Shane and Abhi also cover NVIDIA and Reflection AI, Microsoft's Maia 300 chips, an agent that posted its owner's bank balance to Slack, the Personal Agent Protocol and open source clones of Adobe's apps. Recorded live from the CodeRabbit studio in San Francisco. AI Agents Hour is a weekly livestream by Mastra CPO Shane Thomas and CTO Abhi Aiyer. Mondays 12PM Pacific. 📚 READ MOREOpenAI's recording device: https://x.com/OpenAINewsroom/status/2110095403198849132Mistral Large 4: https://x.com/mistralai/status/2107457414387622310Claude Haiku 5.5: https://x.com/claudeai/status/2107894039626277339Muse Wonder: https://x.com/finkd/status/2109689305073614918Gemini 4 Argon: https://x.com/sundarpichai/status/2110038898009407584OpenAI does math: https://x.com/AndrewCurran_/status/2107596925512065087Jev's Series A: https://x.com/CompleteSkeptic/status/2108594987177021737SubQ Snap: https://x.com/alex_whedon/status/2109676361371824229Microsoft-Decision-1: https://x.com/satyanadella/status/2108627923888754862Clef-omni: https://x.com/cloudflare/status/2108696873510850758Anthropic's in-house source control: https://x.com/AnthropicAI/status/2110047081414987957Claude's new usage policy: https://x.com/haydenfield/status/2108241513159528705Chris Olah and the Pope: https://x.com/christopherhale/status/2106011594182304234NVIDIA and Reflection AI: https://x.com/ns123abc/status/2109007812277743757Maia 300: https://x.com/satyanadella/status/2109631106404487523Grok Bot and Claude: https://x.com/elonmusk/status/2107724314451878104The agent that posted my finances: https://x.com/ShaneMac/status/2107486746325725669Devin Dreaming: https://x.com/cognition/status/2107165034463867001Nous Research raises $90M: https://x.com/choblin29/status/2107801489506750725Personal Agent Protocol: https://x.com/btaylor/status/2107535182119244176Coinbase fine-tunes Qwen: https://x.com/brian_armstrong/status/2109412046244913643Adobe clones: https://x.com/Pirat_Nation/status/2108437553615425881 📚 MASTRA RESOURCESMastra: https://mastra.aiMastra on X: https://x.com/mastra_aiMastra Discord: https://mastra.ai/community/discordMastra GitHub: https://github.com/mastra-aiLearn Mastra: https://mastra.ai/learnPrinciples of Building AI Agents (Book): https://mastra.ai/books/principles-of-building-ai-agentsPatterns 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. ⏱️ CHAPTERS00:00 Cold open00:29 Intro01:37 OpenAI finds a literal bug03:18 Mistral Large 4 aka Le Chonk05:07 Claude Haiku 5.506:28 Muse Wonder08:14 Gemini 4 Argon is out09:06 OpenAI does math11:27 Jev's $870M Series A12:42 SubQ Snap13:12 Microsoft-Decision-113:42 Unsloth and Clef-omni14:06 Anthropic builds its own source control17:32 Cheaper Sonnet, Claude Dashboards and Motion17:50 Be n

Oct 9, 2026

AI agents write code faster than CI can check it. GitHub reports a 4x jump in Actions minutes since 2023, and Anthropic says CI became its biggest bottleneck after job volume grew 25x in six months. Daniel Worku, co-founder and CTO of StarSling, joins Shane and Abhi to talk about what CI looks like when agents write most of the code. Faster hardware helps, but StarSling also runs a background agent, built on Mastra, that A/B tests changes to your CI and opens a PR when it finds a speedup. Daniel explains why agents make CI so expensive: more PRs, piles of low-value unit tests, and stacked PRs that rerun everything. He also makes the case that most unit tests aren't worth running, and that CI as we know it may not survive. You'll also hear how Mastra's own CI went from half-hour waits to a fraction of that, and why code review is the next bottleneck. StarSling's new Review Runners let you bring your own model and run reviews on the same infrastructure as your CI. Recorded live on AI Agents Hour, a weekly livestream by Mastra CPO Shane Thomas and CTO Abhi Aiyer. Mondays 12PM Pacific. 👤 ABOUT DANIELDaniel Worku is the co-founder and CTO of StarSling, a YC company building self-improving CI for GitHub Actions. Before StarSling, he worked in Big Tech and at several startups, most recently at Netflix, where he led the team behind Netflix Console, the company's most used internal developer tool. Daniel on X: https://x.com/dbworkuStarSling: https://starsling.devStarSling Review Runners: https://starsling.dev/products/review-runnersHow Mastra got 6x faster GitHub Actions tests: https://starsling.dev/customers/mastraHigh Performance Sandbox Benchmarks: https://github.com/starslingdev/hpc-sandbox-benchmarksAnthropic on CI and test impact analysis: https://claude.com/blog/agentic-coding-is-straining-ci-heres-how-we-scaled-test-impact-analysis-at-anthropic 📚 MASTRA RESOURCESMastra: https://mastra.aiMastra on X: https://x.com/mastra_aiMastra Discord: https://mastra.ai/community/discordMastra GitHub: https://github.com/mastra-aiLearn Mastra: https://mastra.ai/learnPrinciples of Building AI Agents (Book): https://mastra.ai/books/principles-of-building-ai-agentsPatterns 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. ⏱️ CHAPTERS00:00 Cold open00:23 Why CI became the bottleneck01:25 Meet Daniel and StarSling02:51 Why GitHub's runners are slow03:58 Self-improving CI05:06 Benchmarking sandboxes for CI06:41 Why agents make CI so expensive07:43 Most unit tests aren't useful08:23 Stacked PRs09:25 Mastra's CI story11:48 The end of CI as we know it13:26 Sharing infra between CI and code review14:36 Code review is the new bottleneck15:08 Bring your own model to code review16:27 Outro

Oct 6, 2026

Anthropic's IPO prospectus leaked, showing a $2 trillion valuation target on $4.6 billion in revenue, with a quarter of that coming from two customers. Google is back in the frontier race with Gemini 4 Argon, which tops the Vals Index and can output up to a million tokens at once. Decision models are suddenly everywhere: OpenAI's Decisions API, OpenRouter's new category, Cloudflare's Clef, GLiDE, Respan's Span-01 and Kev. The White House got the big labs to sign an accord on superintelligence, Factory fired an advisor who then became Cognition's CRO, and Vinod Khosla picked a side in public. Shane and Abhi also talk about why maintainers like Sindre Sorhus and Hono are closing external PRs, and go through quick hits including Turso joining Supabase, OpenDots, Conductor Mobile, Karpathy on explainer videos, Claude Code mods, and a video model that passes the Turing test. AI Agents Hour is a weekly livestream by Mastra CPO Shane Thomas and CTO Abhi Aiyer. Mondays 12PM Pacific. 📚 READ MOREAnthropic IPO prospectus: https://x.com/ns123abc/status/2104735822029176833OpenAI Decisions API: https://x.com/thsottiaux/status/2104986448269279399Begun, the clone war has: https://x.com/CompleteSkeptic/status/2105000685209313736OpenRouter decision models: https://openrouter.ai/models?output_modalities=decisionsCloudflare Clef: https://x.com/michellechen/status/2105684868550045751GLiDE: https://x.com/george_onx/status/2105726320357634303Dots: https://x.com/OpenAI/status/2104984504133918973GPT-6.1 Sol: https://x.com/OpenAIDevs/status/2104993067942219873Sam Altman on Cerebras: https://x.com/sama/status/2106147184693620924Gemini 4 Argon: https://x.com/GoogleDeepMind/status/2105388084154056939Vals Index: https://x.com/ValsAI/status/2105388446844072033White House Accord: https://x.com/davidsacks/status/2105060520327786914Factory vs Cognition: https://x.com/matanSF/status/2105335179502064038Vinod Khosla: https://x.com/vkhosla/status/2105382865173459034Sindre Sorhus closes PRs: https://x.com/sindresorhus/status/2105693826690298314Hono closes PRs: https://x.com/yusukebe/status/2107027870019445007Turso joins Supabase: https://x.com/tursodatabase/status/2106054567125532976OpenDots: https://x.com/ataiiam/status/2105710796198322659Conductor Mobile: https://x.com/charlieholtz/status/2105769644498002130Karpathy: https://x.com/karpathy/status/2105819303471976479Claude Code mods: https://x.com/ClaudeDevs/status/2105721434807083061Tavus Griffin: https://x.com/tavus/status/2105704169009246248Eleven v4: https://x.com/ElevenLabs/status/2104572127617994917SWE-sweep: https://x.com/klieret/status/2105670833574465933 📚 MASTRA RESOURCESMastra: https://mastra.aiMastra on X: https://x.com/mastra_aiMastra Discord: https://mastra.ai/community/discordMastra GitHub: https://github.com/mastra-aiLearn Mastra: https://mastra.ai/learnPrinciples of Building AI Agents (Book): https://mastra.ai/books/principles-of-building-ai-agentsPatterns 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. ⏱️ CHAPTERS00:00 Cold open00:26 Intro00:38 Anthropic's IPO prospectus leaks03:13 The decision model era05:03 Cloudflare Clef, SGLang and GLiDE06:09 Span-01 and Kev06:23 Why decision models are good for the industry07:25 OpenAI DevDay recap08:44 The Dots demo backlash10:28 OpenAI and Cerebras11:27 Gemini 4 Argon13:53 Gemini tops the Vals Index14:09 A 1M token output limit15:14 T

Oct 1, 2026

OpenAI DevDay 2026 happened, so Shane and Abhi jumped on a special live episode of Agents Hour to go through everything that was announced and share their takes. The big launch is Dots, OpenAI's always-on personal agent, which arrives right after Grok Bot and Meta's Muse. There's also GPT-6.1 Sol, a speed tier called Ultrafast, Codex Security Cloud, a Decisions API that goes after Jev, computer use in the Agents API, and a lot of new ChatGPT features (Spaces, Pages, slides, meetings) that compete with Google Docs, Notion and a long list of startups. The $200 Pro plan came back with half the usage, next to a new $500 tier. They also talk about choosing your lock-in, what "Sign in with ChatGPT" means for Devin, and the funniest reactions online: the Dots demo flop and xAI buying dot.com to redirect it to Grok Bot. AI Agents Hour is a weekly livestream by Mastra CPO Shane Thomas and CTO Abhi Aiyer. Mondays 12PM Pacific. 📚 READ MOREOpenAI DevDay 2026 recap: https://openai.com/index/devday-2026-recap/Codex Security Cloud: https://x.com/OpenAI/status/2104987422308335828Devin with your ChatGPT subscription: https://x.com/cognition/status/2104996240190792029Pro 200 usage cut and Pro 500: https://thenextweb.com/news/openai-devday-pro-200-usage-cut-pro-500-planMicrosoft Autopilot: https://the-decoder.com/microsoft-gives-copilot-another-makeover-adding-an-autopilot-agent-and-usage-based-billing/The Dots demo: https://x.com/ns123abc/status/2104997638462652838xAI and dot.com: https://www.techbuzz.ai/articles/musk-s-xai-snatches-dot-com-domain-before-openai-s-dots-launch 📚 MASTRA RESOURCESMastra: https://mastra.aiMastra on X: https://x.com/mastra_aiMastra Discord: https://mastra.ai/community/discordMastra GitHub: https://github.com/mastra-aiLearn Mastra: https://mastra.ai/learnPrinciples of Building AI Agents (Book): https://mastra.ai/books/principles-of-building-ai-agentsPatterns 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. ⏱️ CHAPTERS00:00 Intro01:42 Dots04:34 Microsoft Autopilot04:59 GPT-6.1 Sol06:17 Ultrafast06:35 Private Intelligence07:16 Codex in the cloud and code review08:26 Codex Security Cloud09:01 Decisions API10:03 Agents API and Bedrock Managed Agents10:56 Are plugins the new app stores?12:07 MCP events12:42 ChatGPT Space, Pages and more14:06 Sign in with ChatGPT14:16 Pro 500 and the $200 plan14:38 OpenAI Marketplace14:53 Choose your lock-in17:02 Reactions: the Pro plan rug pull17:51 Devin and Codex subscriptions18:57 Pi and Mastra Code19:44 TypeSafe on the Decisions API20:35 The Dots demo flop21:11 xAI buys dot.com21:59 Outro

See all episodes →