thinker:sam-bowmanSam Bowman
Authored papers (1)
LLM auditing agents can recover a planted hidden objective at rates that are modest individually but strong in aggregate: a Claude Sonnet 4 tool-using investigator solves the Marks et al. reward-model-sycophancy auditing game 13% of the time under realistic affordances (all tools, PT+SFT+RL data), and an outer 'super-agent' that aggregates 10 sampled reports lifts this to 42%. The paper builds three agents and three auditing-game environments with researcher-implanted ground truth. The investigator agent uses chat, grep, semantic search and SAE interpretability tools with a 1M-feature SAE. The evaluation agent builds behavioral evals and discriminates quirky from baseline models in 88% of runs across 10 system-prompted quirks, with all 5 runs correct on 7/10. The breadth-first red-teaming agent, run over 255 seed instructions, surfaces 7/10 quirks within the top 60 transcripts, and the investigator also finds 7/10. Ablations show interpretability tools raise win rates from near 0% to 10-20%, partly by steering attention to pretraining data, and an SAE trained on all three datasets never wins. Failures concentrate in fixation on early hypotheses and subtle or hard-to-elicit behaviors. The implication is that replicable agent auditors can serve as scalable proxies for scarce human auditors and as a testbed for comparing affordances, even SAEs. The caveats are dev/test contamination on one environment and artificial implanted behaviors.
More papers — OpenAlex / S2
Affiliations (1)
- Anthropic(institute)
Co-authors (7)
- Rowan Wang4 shared
- Trenton Bricken4 shared
- Euan Ong2 shared
- Evan Hubinger2 shared
- Jeff Wu2 shared
- Johannes Treutlein2 shared
- Samuel Marks2 shared
Their work is cited by (1)
Other inbound relations (1)
- mentionsBuilding and evaluating alignment auditing agents(paper)
Recent mentions (2)
- papers-typedbricken-building-evaluating-4396d7.md
- papers-typedlong-2024-logotic.md