Ep 01 - "I Want Your Product to Enable My Agent"
Recorded June 30, 2026, 2pm Pacific. Live from AI Engineer World's Fair! Fable is still banned (as of recording time, ahem). Advice: Build for agents. We’re still talking about loops, but which loops? And more receipts are demanded. Show Notes 00:01:55 Rhys congrats on getting into YC 00:02:30 IN THE NEWS 00:02:43 GPT-5.6 vs. Fable 5 / Rhys's 48 hours with Fable 00:04:04 Model-naming is going great 00:05:48 "Freedom of intelligence" 00:06:31 Harness-level routing 00:08:06 The "dumb zone" (moo) 00:12:52 Cheaper models are good actually 00:13:17 Model tells in thinking traces & code 00:14:10 PlanetScale security fireside 00:16:03 Bio-risk vs. cyber-risk 00:17:40 Rhys tweets at government officials 00:19:19 Anthropic vs. OpenAI positioning 00:20:33 Dillon on regulation 00:22:06 Bet: models unbanned by next ep? 00:23:14 I DON'T WANT TO USE YOUR AGENT 00:24:45 Should companies put an agent in their dashboard? 00:27:53 Agents in your own harness 00:30:36 Two mega-trends 00:32:29 The primitive is the product (Lenny Pruss) 00:36:18 AI psychosis for normies 00:37:40 Making a product good for agents 00:41:27 Products live or die by the database 00:43:03 Rate limits are our future 00:45:38 LOOPS & SOFTWARE FACTORIES (ROUND 2) 00:48:39 What loops are we even talking about? 00:52:14 "House of cards of inference" 00:53:35 "Someone invented IKEA" 00:54:06 Enterprise NetBeans / SOC 2 00:55:52 Tech debt 00:57:43 "Are you sure?" 00:59:32 RECEIPTS REQUIRED 01:03:05 The "five archetypes" tweet 01:05:08 "Software gardening" 01:07:35 Host predictions on the record 01:10:54 "Every prompt is a spin at the slot machine" 01:12:29 Next episode is workflows 01:13:06 Off-by-one errors (etc.) LINKS / ON-SCREEN REFERENCES, IN ORDER IN THE NEWS Model-tiers image (OpenAI forum) https://us1.discourse-cdn.com/openai1/orig... Claude models page (four model cards) https://claude.com/platform/api Starbucks sizes https://www.starbucks.com/menu/product/409... "Freedom of intelligence" tweet (Quinn Slack) https://x.com/sqs/status/2071690420548198581 Magnitude / harness-level routing https://magnitude.dev Anthropic's "Project Deal" https://www.anthropic.com/features/project... "The Dumb Zone" tweet (Matt Pocock) https://x.com/mattpocockuk/status/20712883... Regulation / CA gov tweet https://x.com/RhysSullivan/status/20716329... Rhys tweets to poke additional bears https://x.com/RhysSullivan/status/20718110... TOPIC - I DON'T WANT TO USE YOUR AGENT "I don't want to use your product's agent (Dillon quote-tweet) https://x.com/dillon_mulroy/status/2070983... Dax's original tweet https://x.com/thdxr/status/207101004221666... Low-level-learning PlanetScale fireside • PlanetScale HQ Live Stream: The Future of ... A wild PlanetScale CTO appears https://x.com/NickVanWig SOCs https://en.wikipedia.org/wiki/Security_ope... Ankur Goyal / Braintrust "two mega-trends" tweet https://x.com/ankrgyl/status/2071329164125... Dillon's reply to Ankur https://x.com/dillon_mulroy/status/2071330... "The Primitive is the Product" - Lenny Pruss, Amplify Partners https://www.amplifypartners.com/blog-posts... "I am a golden god" - "Almost Famous" • I Am a Golden God! - Almost Famous (7/9) M... Rita Kozlov - "Welcome to Agents Week" (the math on scaling agents to the masses) https://blog.cloudflare.com/welcome-to-age... TOPIC - LOOPS & SOFTWARE FACTORIES (ROUND 2) "The Coming Loop" - Armin Ronacher https://lucumr.pocoo.org/2026/6/23/the-com... Dillon's software-design skills repo https://github.com/dmmulroy/skills Rhys tweets at Sam Altman re junior engineers (etc.) https://x.com/RhysSullivan/status/20531777... TOPIC - RECEIPTS REQUIRED shadcn tweet ("Are you sure?") https://x.com/shadcn/status/20690544182473... Theo Brown tweet re moving code agents off laptops https://x.com/theo/status/2071083700385955906 Boris Cherny "five archetypes" tweet https://x.com/bcherny/status/2071379474277... FOLLOW THE HOSTS Dillon Mulroy - https://x.com/@dillon_mulroy / https://dillonis.online / https://twitch.tv/dillon Rhys Sullivan - https://x.com/@RhysSullivan / https://rhys.dev / https://executor.sh Sunil Pai - https://x.com/@threepointone / https://sunilpai.dev CREDITS The Next Token is sponsored by Cloudflare https://www.cloudflare.com Subscribe on YouTube / @nexttokenshow and wherever you get your podcasts.

Keynote: After the AI Hype – What’s Real, and What’s Next - Richard Campbell - 2026

I Hate These...

How to Build a High-Converting AI Voice Agent

Violence Expert: Real Self-Defense Is TERRIFYING

Why AI Tokens are so Expensive - Computerphile

Andrej Karpathy: From Vibe Coding to Agentic Engineering w/ Stephanie Zhan

Dylan Patel — The single biggest bottleneck to scaling AI compute

Unfortunately, You Need to Know What the Jevons Paradox is

10 tips to level up your ai-assisted coding - Aleksander Stensby - NDC Copenhagen 2026

Anthropic's Boris Cherny: Why Coding Is Solved, and What Comes Next

Full Walkthrough: Workflow for AI Coding — Matt Pocock

Ep 00 - “None of My Software Has Gotten Better”

Dwarkesh Patel’s Quest to Learn Everything - Ep. 27

Inside Anthropic, the $965 Billion AI Juggernaut | The Circuit

Billionaire's WARNING: I'm SELLING. The Crash Is Already Here!

AI Bubble: ‘Frontier models have run their course’ | Eli the Computer Guy

Inside the Mind of Anthropic CEO Dario Amodei | The Circuit | Extended Interview

Dylan Patel of SemiAnalysis: Why Hardware-Software Co-Design Is AI's Real 100x

Head of Claude Code: What happens after coding is solved | Boris Cherny

