4 appearances on the backlist front page in the last 30 days.
This was a fascinating project - turns out that LLMs inherit a lot of traits from LLMs they're distilled from, including in subtle ways without clear semantic meaning. This has pretty interesting implications - safety problems in a model in
At the start of this project I assumed that to fix misalignment we mainly needed to intervene on the RL stage of training, and SFT didn't matter much - I was pretty surprised to be wrong! I think these results will plausibly change over t
The work targets vagueness and hallucination in natural-language queries over model activations rather than only optimizing benchmark scores
I had a lot of fun working on this paper - we found an elegant story for why subliminal learning happens! A key intuition in interpretability is that basically every interesting phenomena in LLMs boils down to adding a steering vector. Sub