we are going to train swarms.
read my essay to understand why.
new blog post: why taking inference scaling seriously leads to swarms.
contrary to popular belief, I don't think multi-agent systems are a new scaling axis. they're just structured inference scaling.
Show more
at some point we need to seriously have a discussion about the state of LLM evals.
reading the traces and seeing truly horrible stuff
besides being very powerful, this harness is also really fun to use, btw.
talking to people at the big labs is so boring because they will never tell you anything interesting. really grateful to work at a company that not only allows me to talk about the things I work on, but even encourages me to tweet more and share my ideas
Show more
