Guillermo Rauch

See every agent session in AI Gateway logs. Sessions group requests by conversation, with cost, cache hit rate, and the agent that ran it. Session affinity keeps each one on the provider holding its prompt cache. vercel.com/changelog/ai-gateway-logs-now-show-session-affinity

When I was writing Unreal Engine 1, my time was divided as follows: - Around 30% went to seriously deep coding on hard problems: assembly language texture mappers, C++ BSP trees, data persistence, object oriented systems design, and networking. - Around 70% was just typing and refactoring large bodies of code needed for a complete engine feature set. This was not hard, and while I was doing it my mind was mostly on the deeper coding topics, thinking and planning for what's next. It didn't feel much different from vibe coding today, except that it was just me typing code on an IBM Model M keyboard rather than prompting it and reviewing the results. So, it has always seemed perfectly logical that we would rely on AI for that 70%, once the AI could do it with a similar quality standard as we could, which has never been perfection. It came as no surprise that, after a few years of AI model evolution, it was able to take the reigns on that 70% and free up programmers' time for more valuable tasks. What's more of a surprise is the emergence of AI as a sort of insta-Carmack able to solve hard technical problems quite cleverly and often cleanly, and that it's able to reason about and work in complex 3D scenes both by operating the tools and by directly understanding the raw data files. I abandoned assembly language in 1998 when out-of-order CPUs made much simpler C/C++ code faster, and never I missed it. If prompting through architectural documents, concept art, and design plans can transcend typing code and tweaking vertices, that will enable developers to spend their time on higher-level, higher value technical and creative tasks. What matters is the end product, whether it's a game or an engine. Anything developers can do to try out more ideas and make better software and games faster is a win for everyone.

New from Vercel Labs: tsc-ts TypeScript was written in TypeScript Then rewritten in Go We ported it back to TypeScript Compiled it with scriptc And it's 2-4x faster than tsgo

fx v0.0.14 libfx is now durable out of the box. Same API on local, Vercel and DIY. - Sessions survive crashes, redeploys & timeouts - Power cloud agents with ChatGPT & Grok subscriptions - Custom providers & local model support in libfx - Run multiple libfx agents in one app - More control over each libfx session - TypeScript types for libfx's public APIs - Ported to Zig 0.17 - Multiple bug fixes & security improvements fx.sh/changelog#v0.0.14

Beam from @reflection_ai is free on AI Gateway for a limited time. Until today it ran in stealth as 𝚜𝚝𝚎𝚊𝚕𝚝𝚑/𝚌𝚊𝚝-𝚓𝚊𝚖. It's a low-latency US open-weight model. 𝚛𝚎𝚏𝚕𝚎𝚌𝚝𝚒𝚘𝚗/𝚋𝚎𝚊𝚖-𝚏𝚛𝚎𝚎 vercel.com/changelog/reflection-ai-beam-now-available-on-ai-gateway-for-free

Try Cat Jam for free on AI Gateway. 𝚜𝚝𝚎𝚊𝚕𝚝𝚑/𝚌𝚊𝚝-𝚓𝚊𝚖 • Low-latency inference • Reasoning model for coding & agentic tasks vercel.com/changelog/cat-jam-is-now-available-in-stealth-for-free-on-ai-gateway

Vercel Drives is generally available. You can now run stateful agents on Vercel. vercel.com/blog/introducing-vercel-drives-persistent-storage-for-agents

Vercel Daemons is now in public beta. Run background workers that pull jobs from queues, databases, or third-party systems. vercel.com/changelog/vercel-daemons-is-now-in-public-beta

Run your backend on Vercel. • Python is generally available • Containers for other runtimes & system libraries • Daemons for async jobs & background workers vercel.com/blog/backends-on-vercel-python-containers-and-daemons

We offered $1M to escape Vercel Sandbox. • 1,285 reports • $242,000 in bounties paid out • One Linux kernel zero day discovered • No reports of customer data compromise vercel.com/blog/findings-from-the-1-million-dollar-vercel-sandbox-challenge

Gemini 4 Argon, the first Gemini 4 model, is live on AI Gateway. 50% off through Dec 1st. Use it with difficult coding and agent tasks. 𝚐𝚘𝚘𝚐𝚕𝚎/𝚐𝚎𝚖𝚒𝚗𝚒-𝟺-𝚊𝚛𝚐𝚘𝚗 vercel.com/changelog/gemini-4-argon-now-available-on-ai-gateway

I ported @vercel's fx coding agent to Windows 98 it talks to an LLM over a 56k modem and supports computer use (via MCP.exe) I now proudly run my own gamedev studio from 1999 my agents email each other in Outlook and store code on a network drive (git was not invented yet, sorry) good times

Muse Wonder is live on AI Gateway. New class of larger, more advanced models from @Meta. Built for frontier coding, long-running agents, and advanced computer use. 𝚖𝚎𝚝𝚊/𝚖𝚞𝚜𝚎-𝚠𝚘𝚗𝚍𝚎𝚛-𝟷.𝟶 vercel.com/changelog/muse-wonder-now-available-on-ai-gateway

Part of the quest to make TS with scriptc faster than rust. These are valid TS types and have no semantics in JS, but when compiling with scriptc it will not compile if the function buddy may, indeed, throw. scriptc is already computing this anyway to emit more optimal code, so this is a zero-cost check. You (your clanker) would use this if you want to ensure that code can be compiled optimally.

Introducing Muse Wonder, our new family of frontier models with state of the art performance for personal and professional agentic work.