security1 publisher
An 11-model probe puts the "this is impossible" signal 85 degrees from the refusal direction
Yucheng Du and Xiyang Hu report a single direction that separates answerable from unanswerable math and code prompts at 0.939 mean AUC across 11 models, and its mean cosine with the canonical safety-refusal direction is 0.087.
Publishers:github.com
Reality
- Evidence60
- Adoption
- Insufficient
- Hype gap+12
- Incentives60
- Confidence50