Rob Kopel

Karma: 23

Can a stronger model fake being a weaker one? Mostly not

Rob Kopel14 Jun 2026 17:30 UTC

8 points

0 comments7 min readLW link

(www.robkopel.me)

Exploring capability gated out-of-context reasoning

Rob Kopel9 Apr 2026 5:23 UTC

8 points

0 comments12 min readLW link

(www.robkopel.me)

A push towards interactive transformer decoding

Rob Kopel31 May 2023 17:56 UTC

3 points

0 comments2 min readLW link

(github.com)