Dylan Foster 🐢
djfoster.bsky.social
Incoming professor in EECS and Statistics at UC Berkeley. Principal Researcher @ Microsoft Research NE/NYC. Previously @ MIT, Cornell. AI + RL Foundations. RL Theory Lecture Notes: https://arxiv.org/abs/2312.16730 http://dylanfoster.net
👤 Joined on 21 November 2024
2511
Followers
838
Following
113
Total Posts
📜 Kullanıcı Geçmişi
- 21 Kas 2024, 14:35
🎉 Bluesky'e katıldı - İlk kullanıcı adı:
@djfoster.bsky.social
🚫 Blokladığı Kullanıcılar
❤️ Beğendiği Gönderiler
Mechanistic Interpretability is making the rounds again, so I'm re-upping my ask for a short explainer (under 1,000 words) of how topic modeling is supposed to solve AI safety.
Show Post
Today is the least mad people wil be about AI for a looooong time
Show PostResisting the urge to build a researcher slop leaderboard
Show Postafter trying to buy a GPU node I’m pragmatically becoming an “AI is a bubble guy“ to get the market to crash
Show Post
Look, I'm just happy that the Nobel Prize for Physics wasn't awarded for AI
Show Post