*deep breath* people think I'm joking when I tell them that to develop taste for software they need to have brunch with their friends, watch old movies and find old records, walk around metropolitan cities and observe how the building styles lend to the personality of the people around them, but I'm so fkin dead serious. where else is this mythical "taste" going to come from? what are you doing to parse the human condition? mf you can barely decide what discomfort you're subjecting yourself to in finding out what you like/dislike, and I'm supposed to trust you to make decisions for millions of people? go do some pottery and come back to me and describe the joy you felt without faffing about curves or whatever, I need you to feel the clay under your fingernails and fall in love with mud. even steve had the decency to drop acid on a sweaty beach in goa to find himself, the least you can do is listen to your friends talk about their lives over a meal without getting distracted by your phone. *exhale*

Looking at agents "thinking" feels like having to wait for an image to load pixel by pixel in the early days of the web. John on our team got a docs agent down to a 0.5s median answer by moving decisions from the LLM to @typesafeai's Jev: → Pick the right knowledge base entry (282ms vs. 1,328ms with Haiku) → Guess what the user needs while they're still typing → Send questions to a bigger model only when they need it → Choose the retrieval method Timings and build patterns on our engineering blog: sanity.io/engineering/the-0-…

"JEV-as-a-Judge: Accept When Confident, Escalate When Unsure" This paper shows you can just use JEV for every evaluation instead of expensive LLM. JEV basically acts as a cheap first-pass judge, returning both a verdict and how confident it is. When confidence is high, keep the answer. When it’s low, escalate to a stronger LLM. This simple routing keeps ~99% of GPT-6’s accuracy while reducing evaluation cost by a lot. alphaxiv.org/abs/2609.26550

Are you unable to use Safari because of dizzying wobbly spinners? Me too! 😤🤌 Start using the new CSS `round()` function and fix your app (like we did sanity.io/engineering/we-fix…) so we can all use Safari again (and not just Ash!) 😮‍💨🏖️

We're adding support for AGENTS.md to Claude Code. Starting today in version 2.1.277, if there is no CLAUDE.md in a folder, Claude will check for and use AGENTS.md. You can toggle this behavior in /config.

The idea of the “LLM knowledge base” is powerful, but how do you bring it into organizational contexts?