arav-dhoot

Karma: 94

Where does hint-following and concealment arise? A case study on OLMo-3 checkpoints

arav-dhoot and yix

24 Jul 2026 19:14 UTC

24 points

0 comments4 min readLW link

LLM CoTs remain monitorable when being unfaithful requires computation

arav-dhoot and yix

15 Jul 2026 21:14 UTC

46 points

3 comments7 min readLW link

(secondlookresearch.com)

Failing to Ragebait the New Gemma

Neil Shah, David Africa and arav-dhoot

11 Jun 2026 17:50 UTC

31 points

0 comments3 min readLW link

Two More Methods for Consistency Training and Some New Ways to Apply It

David Africa, Sukrati_Gautam, Neil Shah and arav-dhoot

5 Jun 2026 21:06 UTC

25 points

0 comments7 min readLW link