Avoiding steering awareness by optimizing steering parameters

·LessWrong··

Steering effectiveness and detection depend heavily on the target concept and model combination. Why this is a concern for safety evaluations and how to mitigate it.TL;DR:Recent research provides robust evidence about models being able to detect steering being performed on them.This capability could help the model infer it’s being evaluated and elicit unwanted or unexpected behavior that might compromise benchmarks or evaluations employing steering as a measurement tool.The relationship between ...

Read full article →

Related Articles

Every AI model has the same "controversial" take on humans
rakannimer · Hacker News · 1d ago
UUIDv7 doesn't have the properties you think it does
ibobev · Hacker News · 6h ago
Pentagon grants DHS permission to test heat ray weapon for use at border
bushwart · Hacker News · 8h ago
Jailbreaking the Switch 2
ledoge · Hacker News · 1d ago
The 1.5°C goal of the Paris Agreement is no longer viable
velo_aprx · Hacker News · 2d ago