Daily Brief

In this session, we'll be building a coding agent that implements ACP — covering protocol design, session lifecycle management, and handling tool calls. The session ends with a live demo of the finished agent running inside Zed, showing what ACP looks like in practice from both sides of the protocol.

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

Your agent is blindfolded. How giving it (good) eyes multiplies performance and trust!

With the recent development of AI, either you or your friend probably vibe coded a game using Gemini, on Three.js. But that is old news now. If everyone can do that, what is next? The next massive hit, the one that millions of people across the world will play, is just about to be born. Wanna know more? Come see this talk!

For the closing keynote of AIEWF2026, Theo provokes you to think wider, not just bigger. In this keynote from the AI Engineer World's Fair, developer and YouTuber Theo Browne (@t3dotgg) argues that the rapid evolution of AI models—moving from tool-calling (Sonnet 3.5) to long-running task execution (Opus 4.5) and now orchestration (Mythos)—requires software engineers to fundamentally change how they build products. Key Themes: Rejecting Skeuomorphism: Browne compares the current state of software development to the design shift in iOS 7, urging developers to move away from legacy mental mode

Tarek Mansour calls himself a paranoid risk manager - the guy who can list 20 ways a hot air balloon will go down before it leaves the ground. Then he bet his entire company on suing its own regulator. Kalshi spent years walking through the desert. The CFTC pocket-vetoed its election markets ahead of the 2022 midterms, people left, and the company took a layoff while the government piled on audits and enforcement actions. Death by a thousand paper cuts. Instead of pivoting, Tarek and co-founder Luana Lopes Lara sued the federal government against the guidance of nearly all their investors and

Every company has one leak the founder can't hand off. Tarek Mansour explains why most CEOs throw a rug over theirs — and why Kalshi's is proving what separates regulated prediction markets from the offshore players. #shorts #ceo #entrepreneur

OpenAI's Dev Day 2024 demo ran on an o1 preview model that could not run or check its own code, so Romain Huet had to cross his fingers live on stage. A year later, the same kind of demo ran a full camera and lighting rig, because the model could now test its own work. Alexander Embiricos and Huet use that jump to show how fast Codex is moving: new model releases went from every 15 months to about every 6 weeks. They walk through why Codex is built on the same responses API, open source harness, and AGENTS md file format that ships to every developer, plus new numbers on cost and speed: front

From adding GPUs a year before ChatGPT to building the cloud primitives behind elastic inference, agent sandboxes, post-training, and production AI workloads, Modal has quietly become one of the most important infrastructure companies in AI. In this episode, Modal CTO Akshat Bubna joins swyx and Vibhu after Modal’s Series C to unpack why AI applications don’t fit traditional cloud assumptions, why Kubernetes was never designed for bursty compute-heavy workloads, and why Modal is now shifting from developer experience to agent experience. We go deep on Modal’s AI infra stack: serverless functi