Peter Hase
peterbhase.bsky.social
Visiting Scientist at Schmidt Sciences. Visiting Researcher at Stanford NLP Group Interested in AI safety and interpretability Previously: Anthropic, AI2, Google, Meta, UNC Chapel Hill
👤 Joined on 01 December 2024
517
Followers
450
Following
8
Total Posts
📜 Kullanıcı Geçmişi
- 01 Ara 2024, 20:00
🎉 Bluesky'e katıldı - İlk kullanıcı adı:
@peterbhase.bsky.social
🚫 Blokladığı Kullanıcılar
❤️ Beğendiği Gönderiler
🎉 Congrats @peterbhase.bsky.social + best wishes for the @schmidtsciences.bsky.social scientist + @stanfordnlp.bsky.social visiting researcher roles! 🙂 Looking forward to your continued exciting research contributions in AI safety & interpretability, and your new grant-making contributions 🔥
Show Post
Rolling this out just days after Grok declared itself MechaHitler is really something.
Show Post
SAEs have been found to massively underperform supervised methods for steering neural networks. In new work led by @danaarad.bsky.social, we find that this problem largely disappears if you select the right features!
Show Post