Auditors Struggle to Catch Sabotage in End-to-End Transcripts of AI Safety Research
keshavs
Abstract
Authors: Keshav Shenoy, Anthony Zang, Eric Gan, Jacqueline Tay, Amy Ngo, Sebastian Prasanna, Julian Stastny, Vivek Hebbar tl;dr. We had a human expert secretly sabotage AI safety research and asked auditors to spot it. Even with the full research log and the ability to run their own experiments, human auditors could barely tell sabotaged research from benign research, and usually couldn't pin down what had been sabotaged. The best frontier models likely do better, but still miss most of the sabotage. 📄 Paper | 🐦 Twitter Introduction As AI systems automate more of AI R&D, a misaligned AI could covertly sabotage AI safety research. This sabotage could take many forms, including making poor methodological choices, introducing subtle bugs, omitting important results, or drawing conclusions the evidence doesn't support. Prior work has studied sabotage in controlled settings ( Libon et al., 2026 ; Gan et al., 2026 ), but these settings constrain the saboteur in unrealistic ways, such as pre-specifying its objective, narrowly scoping its task, or limiting it to low-level changes. Much less is known about research sabotage when an adversary is free to choose its own strategy across the f