RSS

David Scott Krueger (formerly: capybaralet)

Karma: 2,165

I’m more active on Twitter than LW/​AF these days: https://​​twitter.com/​​DavidSKrueger

Bio from https://​​www.davidscottkrueger.com/​​:
I am an Assistant Professor at the University of Cambridge and a member of Cambridge’s Computational and Biological Learning lab (CBL). My research group focuses on Deep Learning, AI Alignment, and AI safety. I’m broadly interested in work (including in areas outside of Machine Learning, e.g. AI governance) that could reduce the risk of human extinction (“x-risk”) resulting from out-of-control AI systems. Particular interests include:

Grad­ual Disem­pow­er­ment: Sys­temic Ex­is­ten­tial Risks from In­cre­men­tal AI Development

30 Jan 2025 17:03 UTC
152 points
50 comments2 min readLW link
(gradual-disempowerment.ai)

A Sober Look at Steer­ing Vec­tors for LLMs

23 Nov 2024 17:30 UTC
37 points
0 comments5 min readLW link

[Question] Is there any rigor­ous work on us­ing an­thropic un­cer­tainty to pre­vent situ­a­tional aware­ness /​ de­cep­tion?

David Scott Krueger (formerly: capybaralet)4 Sep 2024 12:40 UTC
19 points
7 comments1 min readLW link

An ML pa­per on data steal­ing pro­vides a con­struc­tion for “gra­di­ent hack­ing”

David Scott Krueger (formerly: capybaralet)30 Jul 2024 21:44 UTC
21 points
1 comment1 min readLW link
(arxiv.org)

[Link Post] “Foun­da­tional Challenges in As­sur­ing Align­ment and Safety of Large Lan­guage Models”

David Scott Krueger (formerly: capybaralet)6 Jun 2024 18:55 UTC
70 points
2 comments6 min readLW link
(llm-safety-challenges.github.io)