Daily Brief

Sharing a few thoughts on the future of math These videos are funded directly by viewers: https://3b1b.co/support An equally valuable form of support is to simply share the videos. Home page: https://www.3blue1brown.com If you want a finger on the pulse of how mathematicians are feeling right now, take a look at this post on Proofs and Prompt: https://proofsandprompts.com/2026/10/08/100-reactions-to-100-solutions/ Timestamps 0:00 - Math student angst 3:10 - How does math work? 11:24 - A proof machine 25:12 - A conjecture machine 26:59 - A theory machine 31:31 - If AI is better at everything

Ken Thompson built Unix in a month. IBM put 1,000 engineers on OS/360. And in 1998, Linus Torvalds hit his limit. Now we're hitting that same wall managing AI agents. Anthropic's CJ Avilla and Harrison Stall introduce Flows in Claude Managed Agents. You hand Claude a goal, and it plans and runs its own multi-agent topology of up to 1,000 agents through the API. In this hands-on workshop they demo a stock watchlist scanner, show how to spend more compute on the phases that matter, walk through the Bug Hunter and Explainer Studio templates, and explain why single agents fail through laziness, s

Full episode: https://www.youtube.com/watch?v=f6cjAEr08qk Me on twitter: https://x.com/dwarkesh_sp

The model is the part you can't change. The harness around it is where you can make real gains. Nacho Martinez walks through the full agent stack (agent loop, short- and long-term memory, context engineering, the toolbox and skillbox patterns, skill distillation and continual learning) and applies it to an autonomous agent that flags suspicious bank transactions around the clock. 🎟️ Join us at the next one: AIE CODE Summit → https://aie.codes Speaker Nacho Martinez — LinkedIn: https://www.linkedin.com/in/jasperan/ GitHub: https://github.com/jasperan Oracle — https://www.oracle.com Workshop

If your token spend keeps going up and productivity isn't keeping pace, start here. Eugene Cheah lays out four steps for cutting AI inference costs at scale: measure, right-size, buy capacity well and check your processes. Along the way he covers splitting API keys per team, agentic vs. process workloads, open models that match frontier models on specific tasks, classifiers, fine-tuning, the speed-vs-cost tradeoff and "slop grenades." Recorded live at AI Engineer NYC 2026. 🎟️ Join us at the next one: AIE CODE Summit → https://aie.codes Speaker Eugene Cheah — X: https://x.com/picocreator Fea

Fast answers are easy to get. Answers you can trust with your money are harder. Francesco Galletta and Felippe Felisola Caso build a financial-analyst agent harness live, using one real problem: paying for a wedding. They show the five design principles they use for AI you can trust: shared domain, consistency, evidence, accountability and verification. They also explain why calculations belong in code instead of in the model's head. Note: the speakers work at Monzo but are not presenting on Monzo's behalf. 🎟️ Join us at the next one: AIE CODE Summit → https://aie.codes Speakers Francesco G

Your AI agent wrote a confident stock report saying 116% of analysts agree. Nothing in your checks caught it. This is the workshop for fixing that. Laurie Voss (Head of Developer Relations at Arize AI, co-founder of npm) builds a full evals loop on a Claude-powered financial analyst agent: trace it with Arize Phoenix, read the traces, write code evals and LLM-as-a-judge evals, test whether the judge can be trusted, prove a prompt fix with experiments, upgrade from Claude Haiku 4.5 to 5.5 with evidence, and gate it all in CI with npm test. Speaker: Laurie Voss, Head of Developer Relations, Ar

Six AI power users compare what actually works—and what falls apart once you start using it. Ben Davis, Ben Hylak, Dex Horthy, Allison Durham, Alex Volkov, and swyx discuss OpenAI DevDay, coding agents, personal assistants, model preferences, and the gap between impressive AI capabilities and useful products. From Pi-powered personal agents and decision models to subagents, context management, prompt injection, and assistants that can spend money: what deserves a place in your daily workflow? CHAPTERS 00:00 High Taste Testers 01:26 OpenAI DevDay: Dots, Spaces, and product execution 10:28 Gr