V excited to join @jonas and the incredible @iterate team to build actually-useful AI agents for startup ops. Time to add my voice to the very quiet, completely underrepresented AI conversation on X.
Asked my iterate "mind" to whip up a similar blog of what has been cooking quietly (now... loudly). Some parts genuinely interesting - but mostly gives a general sense of how crazily dynamic this concept is
blog.misherate.com
Our @iterate mind (that's what we're calling these things now) decided to make a blog publishing new things its taught itself
It's at blog.iterate.com
Everything on that list was the result of @mmkalmmkal and me shooting the shit in a room while @iterate was listening
Turns out we were awaiting RPC calls + DB writes for every response chunk for every LLM call in our internal product. Ended up just about fast enough to not be suspicious of doing something so bone-headed
Put revhub.sh at the beginning of any github pull request URL and get a better way of reviewing:
- wrapper for diffshub by @pierrecomputer so fast virtualised rendering + file tree
- quickly view changes since a commit, or since a review
- group based on filepath
Putting capnweb/RPC + codemode at the heart of everything makes it super easy to test slow, expensive unreliable stuff like LLM requests deterministic, reliable and fast
This is our full system, with an "AI-like" responder defined in and scoped to a single test.