AI brief
The author describes returning to the safety field after four years and cites their NeurIPS paper on concept distillation, which found that steering-vector-based methods did not help debias a model because the concepts themselves were understood wrongly.
Written by AI from LessWrong's published text.
Source
“Getting back in the safety field after 4 years feels great. I had a paper on concept distillation where I showed how steering vectors based method did'nt help to debias model since the concepts itself are understood wrongly [ Concept distillation , NeurIPS…”
Interpretation or community commentary rather than straight reporting.
Read original story ↗