Ian McKenzie

Karma: 304

Layered AI Defenses Have Holes: Vulnerabilities and Key Recommendations

smallsilo, Ian McKenzie, Oskar Hollinsworth, Tom Tseng, Xander Davies, scasper, Aaron Tucker, Robert Kirk and Adam Gleave

4 Jul 2025 0:07 UTC

13 points

1 comment4 min readLW link

(far.ai)

Does robustness improve with scale?

ChengCheng, niki.h, Ian McKenzie, Oskar Hollinsworth, Tom Tseng and AdamGleave

25 Jul 2024 20:55 UTC

14 points

0 comments1 min readLW link

(far.ai)

Inverse Scaling Prize: Second Round Winners

Ian McKenzie, Sam Bowman and Ethan Perez

24 Jan 2023 20:12 UTC

58 points

17 comments15 min readLW link

Inverse Scaling Prize: Round 1 Winners

Ethan Perez and Ian McKenzie

26 Sep 2022 19:57 UTC

93 points

16 comments4 min readLW link

(irmckenzie.co.uk)

Beliefs and Disagreements about Automating Alignment Research

Ian McKenzie24 Aug 2022 18:37 UTC

107 points

4 comments7 min readLW link

Announcing the Inverse Scaling Prize ($250k Prize Pool)

Ethan Perez, Ian McKenzie and Sam Bowman

27 Jun 2022 15:58 UTC

171 points

14 comments7 min readLW link

Pong from pixels without reading “Pong from Pixels”

Ian McKenzie29 Aug 2020 17:26 UTC

17 points

1 comment7 min readLW link