Gerard Boxo

Karma: 97

Automating AI Safety Research: 1 Managing expectations

Gerard Boxo14 Sep 2026 17:56 UTC

4 points

0 comments4 min readLW link

Three years of progress in 500 lines of code

Gerard Boxo6 Aug 2026 18:27 UTC

65 points

4 comments4 min readLW link

Gerard Boxo’s Shortform

Gerard Boxo4 Jan 2026 13:15 UTC

2 points

4 comments1 min readLW link

[Question] Are Sparse Autoencoders a good idea for AI control?

Gerard Boxo26 Dec 2024 17:34 UTC

3 points

4 comments1 min readLW link

It’s important to know when to stop: Mechanistic Exploration of Gemma 2 List Generation

Gerard Boxo14 Oct 2024 17:04 UTC

9 points

0 comments6 min readLW link

(gboxo.github.io)