When Anthropic released a complex 30K word doc and said Claude was trained to follow it, I was pretty sceptical. Turns out it kinda works! We red teamed Claude's constitution following, and it's gotten much better! Positive update for the ability to align models in nuanced ways

What a time to be alive

the codex team has claude personality and the claude code team has codex personality

agent skills is the wrong abstraction MCP is the wrong abstraction

the real treasure was the slops we made along the way

people are sleeping on generative UI

skills is still not sitting right with me as a concept i think it's because companies rushed to them as the next big thing as is what happens with all ai things now everyone is their docs as skills but it's recreating all the issues (authority, up to dateness) docs solved

AstralCodex sounds familiar 🧐

im sorry to announce: the new Cursor "Glass" desktop app framemogged all other agentic IDEs. best-in-class UI/UX, period. waaaay ahead of codex, opencode desktop, conductor etc. i should never have doubted you, Ryo Lu

she soc 2 on my compliance

this is actually quite cool

Issue tracking is dead. We are building what comes next. linear.app/next

why is everyone building everything

finally someone does it

funniest thing i’ve seen this week

Your SOC2 compliance is fake, your deploy platform leaks private user data, and your HTTP library has malware in it. Happy Monday.

why US users only :(