Dylan Hadfield-Menell
@dhadfieldmenell.bsky.social did:plc:nb2yl632b2ieropxghx3evxx
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/
Bluesky’a katılma tarihi:
- Takipçi
- 4.057
- Takip edilen
- 275
- Post
- 27
- Sıralamaya girdiği gün
- 0
Özet
Dylan Hadfield-Menell (@dhadfieldmenell.bsky.social), 22 Haziran 2023 tarihinde katılan bir Bluesky kullanıcısı. 4.057 takipçisi var, 275 hesabı takip ediyor ve 27 post paylaştı.
Sıralama geçmişi
Bu hesabın postlarının Debya günlük listesine girdiği en iyi günler.
Bu hesap henüz günlük sıralamaya girmedi.
Son beğendiği postlar
Bluesky ağındaki herkese açık beğeniler.
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
Postu göster"These people are really annoying and/or weird" is not actually an argument against their point
Postu gösterI think science supports researchers in several areas including safety. Specifically strategic research implementation. This includes areas such strategic safety strategies.
Postu gösterIt’s holding up quite well. I’m impressed and pleased!
Postu gösterOpus 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.
Postu göster
Blokladığı hesaplar
Bluesky’da bloklar herkese açık kayıtlardır.