Viewing profile — gregfrank

[dead]

[dead]

"Trendslop" is a great name for something I think is a deeper structural problem than it appears. The issue isn't just that LLMs produce generic outputs, it's that our evaluation m…

This framing points at something important that I think the alignment evaluation literature often misses: the distinction between what a model represents internally and what it doe…

The "linear" assumption here is worth interrogating. In work I've been doing on alignment evaluation, I find that linear probes can achieve high accuracy on refusal-relevant direct…