AI brief
A researcher returning to safety work describes a paper on concept distillation finding that steering-vector methods did not debias a model because the underlying concepts were misunderstood.
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 ↗