RSS

ryanothnielkearns

Karma: 15

Oxford Human-Centered AI Lab, Oxford Internet Institute, Cosmos Institute

LLMs Don’t Know Their Own De­ci­sion Boundaries. Why Is This Im­por­tant?

harrymayne and ryanothnielkearns
17 Sep 2025 16:39 UTC
9 points
0 comments5 min readLW link
(arxiv.org)

Are re­cent LLMs bet­ter at rea­son­ing or bet­ter at mem­o­riz­ing?

Jude Khouja, harrymayne, ryanothnielkearns and karolinakorgul
7 Mar 2025 2:44 UTC
11 points
0 comments4 min readLW link