Boris Cherny

Everything, newest first — across every channel. Their profile →

json-schema-to-typescript — Compile JSON Schema to TypeScript type declarations 1 Sept
Fable 5.1 is our best model yet for coding, data analysis, computer use, design, presentations, Tag, and the hardest long-running agentic work. This model is a… 1 Sept
A small improvement: memory is now simpler and more powerful. Enjoy! 25 Aug
We've been working on this with customers for a while. Mythos-class models require additional safety measures and enterprises need to meet their own privacy an… 20 Aug
The small quality of life improvements keep coming. When you’re using Desktop every day, slow startup makes the app feel sluggish. Working on improving this ev… 19 Aug
Small quality of life improvements like this add up. More on the way 18 Aug
Let us know what you think! 18 Aug
A weird experiment I've been trying the last few weeks is having Claude take over day-to-day maintenance of our apps. Seeing early signs of life that this migh… 13 Aug
LLMs still produce bugs, but those bugs are different than what they used to be. It’s less off-by-ones and more about system design, ui usability, missing broa… 11 Aug
Prompt injection is the most common way that scammers attack people and agents: your agent visits https://t.co/5ZWbR4ts4m, and the website has malicious text l… 9 Aug
turns out you can get indirect prompt injection to ~0 on unseen attacks if you stack enough layers (model training + input probes + a classifier checking inten… 7 Aug
The team and I use Auto mode exclusively, and have been for many months. I couldn't imagine going back to permission prompts! Really excited to get this out to… 7 Aug
Opus 5 is a great model for coding, data analysis, design, biology, knowledge work. More than any of these eval scores, what is most exciting to me is somethin… 24 Jul
I talk to engineers at other companies every day and hear the same thing: one person is 10x'ing their output with Claude but the rest of the org hasn't caught… 17 Jul
Something I have been thinking about: in the past, the best engineers I knew spent a lot of time automating their work in various ways. Better vim/emacs automa… 15 Jul
This is pretty epic 8 Jul
New in Claude Code: /checkup Run /checkup to: 1. Clean up unused skills/MCPs/plugins and save context 2. Dedup your local CLAUDE.md against the checked in CLAU… 8 Jul
This is our first time telling the story of how we first built and launched Claude Code, starting with its origins in Anthropic safety research. So much more t… 6 Jul
Artifacts in Claude Code have been life changing. Excited to expand to Pro and Max! 2 Jul
Agree 30 Jun
The scarce skill is now context switching across parallel agents, not sustained deep work. 4 Mar
Working prototypes have replaced product requirement documents. 4 Mar
A migration must be finished once it is started, because a half-migrated codebase confuses models as much as it confuses people. 4 Mar
With a good enough plan, a coding agent implements the whole change in one attempt. 4 Mar
Build for the model six months from now, not the model of today. 25 Feb
bcherny.github.io — My blog 19 Feb
redirect-claude 12 Jun 2025
anthropic-stream-repro 4 Jun 2025
undux — ⚡️ Dead simple state for React. Now with Hooks support. 8 May 2025
mcp-ping 12 Dec 2024
es-module-stats — Collecting statistics on how the internet uses ES modules 19 Jun 2024
json-schema-to-typescript-browser — Browser demo for json-schema-to-typescript 2 Jun 2024