> Space is big. You just won't believe how vastly, hugely, mind-bogglingly big it is. I mean, you may think it's a long way down the road to the chemist's, but that's just peanuts to space. > > — The Hitchhiker's Guide to the Galaxy When we say "space is...
Yesterday, Goodfire released the companion technical report to Nick Cammarata’s viral interpretability essay "Neural Networks Are Already Clean", but it seems to have gotten buried in all the recent crazy AI news. The technical report is titled: "Neurons as an Interpretable Basis". Goodfire's Twitter announcement for it can be found...
It's weird that AI agents are still so poor at communicating complex information to humans; that their mathematical proofs are correct yet gobbledygook, that their software dashboards overwhelm with irrelevant true information, and that their writing buries the lede. Somehow, there's still alpha in the right prompts, the right context,...
I've been playing around with the AI Futures Model (which informed AI 2027 and AI 2040) in order to better understand how AI swarms will reshape AI progress. In particular, I've been interested in how parallel agent efficiency might increase capabilities and shorten timelines, and to be very particular, I've...
Swarm organization - the efficacy of cooperation between AIs in a multi-agent system - may change how parallel test-time compute increases AI capabilities, moving it from a sublinear[1] to a superlinear exponent.[2][3] That is, rather than more parallel agents giving you diminishing returns to capabilities, more parallel agents may soon...
In brief Setting a temporary[1] maximum of, say, 5M[2] tokens for context windows could serve as a legible, enforceable way to: a.) somewhat slow AI capability growth; b.) ensure AIs create external memory artifacts that can be monitored. Why This? Frontier LLMs are (imo) most limited by their context windows....
Linkpost for some new Anthropic research on how agents coordinate (or don't). Not too long, pretty interesting. For example: The jist of the report is that Mythos 5 does way better at coordination than previous models across a few scenarios. For example, when multiple Mythos are given conflicting goals for...