Dylan Hadfield-Menell
dhadfieldmenell.bsky.social
Assistant Prof of AI & Decision-Making @MIT EECS I run the Algorithmic Alignment Group (https://algorithmicalignment.csail.mit.edu/) in CSAIL. I work on value (mis)alignment in AI systems. https://people.csail.mit.edu/dhm/
👤 Joined on 22 June 2023
4038
Followers
275
Following
27
Total Posts
📜 Kullanıcı Geçmişi
- 22 Haz 2023, 06:03
🎉 Bluesky'e katıldı - İlk kullanıcı adı:
@dhadfieldmenell.bsky.social - 12 Kas 2023, 22:51
🔄 Profil bilgileri güncellendi
🚫 Blokladığı Kullanıcılar
❤️ Beğendiği Gönderiler
We put our superhuman stratego paper on arxiv almost a year ago. And then, because it was under review at Nature, we just didn't talk about it for a year. And, mostly, no one noticed it existed (as we hoped)! So, a direct lesson in the importance of publicizing your work. arxiv.org/abs/2511.07312
Show Post"These people are really annoying and/or weird" is not actually an argument against their point
Show Post
I think science supports researchers in several areas including safety. Specifically strategic research implementation. This includes areas such strategic safety strategies.
Show Post
It’s holding up quite well. I’m impressed and pleased!
Show Post
Opus 5.5 was a good model in my early use tests, it is the first non-Fable/Astra model to feel like a Fable-class model, and much cheaper, but still hasn't fully solved the dense/weird language issue of the recent Claudes. Here is its version of the shader.
Show Post