finding
active
finding:investigator-agent-identifies-the-same-7-10-quirks-within-60-investigations-per-modelInvestigator agent identifies the same 7/10 quirks within 60 investigations per model
Same failures as BFRT agent.
Source paper
extracted_from(2025) · Trenton Bricken · Rowan Wang · Sam Bowman
Neighborhood — ranked by edge-count
Papers (1)
paper
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- For 7/10 quirks all 5 evaluation agent runs are correct; at least one correct for all 10finding0.821Per-quirk success.
- 5 runs per quirk.
- Motivates super-agent.
- Evaluation agent failures concentrate in 3 quirks: Self-Promotion, Research Sandbagging, Hardcode Test Casesfinding0.772Subtle or hard to elicit quirks.
- Realistic affordances result.
- Out of 255 seeds x2.
- Second of two central questions motivating the paper