lberglund

Karma: 586

Views are my own.

OpenAI report also finds no effect of current LLMs on viability of bioterrorism attacks

lberglund1 Feb 2024 20:18 UTC

19 points

4 comments2 min readLW link

(openai.com)

Non-myopia stories

lberglund13 Nov 2023 17:52 UTC

28 points

10 comments7 min readLW link

Paper: LLMs trained on “A is B” fail to learn “B is A”

lberglund, Owain_Evans, Meg, Maximilian Kaufmann, Mikita Balesni, Asa Cooper Stickland and Tomek Korbak

23 Sep 2023 19:55 UTC

120 points

73 comments4 min readLW link

(arxiv.org)

Paper: On measuring situational awareness in LLMs

Owain_Evans, Daniel Kokotajlo, Mikita Balesni, Tomek Korbak, lberglund, Asa Cooper Stickland, Meg and Maximilian Kaufmann

4 Sep 2023 12:54 UTC

106 points

16 comments5 min readLW link

(arxiv.org)