RSS

Danielle Ensign

Karma: 206

The LLM Has Left The Chat: Ev­i­dence of Bail Prefer­ences in Large Lan­guage Models

Danielle Ensign8 Sep 2025 0:57 UTC
87 points
4 comments5 min readLW link

Un­su­per­vised Ac­ti­va­tion Steer­ing: Find a steer­ing vec­tor that best rep­re­sents any set of text data

Danielle Ensign6 Jun 2025 22:37 UTC
3 points
2 comments1 min readLW link

Ophiol­ogy (or, how the Mamba ar­chi­tec­ture works)

Danielle Ensign, SrGonao and Adrià Garriga-alonso
9 Apr 2024 19:31 UTC
67 points
10 comments10 min readLW link

Hu­man Bi­ases that Ob­scure AI Progress

Danielle Ensign25 Sep 2020 0:24 UTC
48 points
2 comments4 min readLW link