Patrick Hussey (@PatrickRiot) header
Patrick Hussey (@PatrickRiot) profile picture

Does https://nitter.cf/t.co/oN8uWF92MG, writes https://nitter.cf/t.co/mxbsQzkvo5, made https://nitter.cf/t.co/JWeBJ5Uy3G. Interested in Ai for public good. Which is complex.

London
Joined February 2009
Photo by Patrick Hussey (@PatrickRiot)Photo by Patrick Hussey (@PatrickRiot)Photo by Patrick Hussey (@PatrickRiot)Photo by Patrick Hussey (@PatrickRiot)Photo by Patrick Hussey (@PatrickRiot)Photo by Patrick Hussey (@PatrickRiot)Photo by Patrick Hussey (@PatrickRiot)Photo by Patrick Hussey (@PatrickRiot)Photo by Patrick Hussey (@PatrickRiot)Photo by Patrick Hussey (@PatrickRiot)
GOVERNMENT: Anthropic’s proposed AI safety bill only kicks in if 50 deaths or $1 billion in damages are on the line — proposal would effectively make the Commerce Department the only agency capable of stopping an AI model tomshardware.com/tech-indust…
1
1
17
Patrick Hussey retweeted
interpretability might be the most important scientific problem in the world right now, as I don't think we can solve alignment if we don't know what we're building. I think I have good news about it. I co-authored early work in mechanistic interpretability at OpenAI and came away pessimistic, because neural networks appeared to fold into arbitrary tangled knots. years later, I started openai's first large-scale automated interpretability project, finding about 2% of neurons legible with the primitive tools we had with modern agentic tools and a much closer look, the picture looks totally different. the vast majority in models up to trillions of parameters are legible, and their circuits beautiful. many famous examples of tangled neurons turned out to be misunderstood. The roadblocks I expected mostly aren't there. I now think ambitious interpretability will be solved by the time we need it most, and possibly quite soon, as automated scientists keep improving. it may be a bitter lesson for interpretability: the simple thing, at absurd scale, works already-clean.goodfire.com/
890
2,657
1,464
19,998
4,815,120
Today's five important AI stories across sectors. Read the stories and sign up for AI Daily: everythingmeetsai.com/newsle…
2
2
20