Eval-Awareness Steering detects the Test, Not the Sabotage

·LessWrong··

Produced as part of independent researchHuge thanks to Apollo Research (org) for open-sourcing the deception-detection harness which proved to be foundational in this work. Prior work by Devbunova (2026), the Apollo/Goldowsky-Dill probing line, and Tice et al. on noise injection shaped the design throughout.SummaryI test whether the internal "I'm being evaluated" direction in an open-weight model causally drives sandbagging (deliberate underperformance) or merely correlates with it. I reuse Apol...

Read full article →

Related Articles

Unauthenticated remote code execution in Nginx
speedping · Hacker News · 6h ago
Highly classified US national security communications network goes down
monkeydust · Hacker News · 1d ago
Harvard researchers find AI coding agents shifted the bottleneck to code review
judahmeek · Hacker News · 1d ago
New Evidence Shows School Phone Bans Are Gradually Improving Test Scores
donohoe · Hacker News · 1d ago
Java4Shell: RCE in OpenJDK when processing Base64
werrett · Hacker News · 1d ago