Nick Merrill

Karma: 59

AI Researcher @ FRI, previously U.C. Berkeley CLTC. https://else.how

AIRO: Automated forecasts of catastrophic risks

Nick Merrill11 Sep 2026 16:29 UTC

12 points

0 comments3 min readLW link

Llama will abandon a correct answer if it thinks you’re educated

Nick Merrill20 Aug 2026 20:06 UTC

33 points

7 comments2 min readLW link

Defeating Introspection Adapters (and Why Threat Models Matter)

Nick Merrill and zekem

4 Jun 2026 18:39 UTC

10 points

0 comments5 min readLW link

Emergent introspection does not replicate on Llama-3.1-405B

Nick Merrill11 May 2026 4:05 UTC

9 points

3 comments6 min readLW link