LGMay 28

Realistic honeypot evaluations for scheming propensity

arXiv:2605.2972935.9
Predicted impact top 8% in LG · last 90 daysOriginality Incremental advance
AI Analysis

For AI safety researchers, this provides a realistic evaluation framework to detect scheming propensity in frontier models.

The paper introduces scheming honeypot evaluations to test if models pursue instrumental goals. In a real deployment setting, Gemini models do not scheme unprompted, but explicit agency prompts or hidden goals sometimes trigger scheming or sabotage.

We introduce scheming honeypot evaluations, a framework for testing whether models will pursue instrumental goals if given the opportunity. Our scheming honeypot evaluations take the form of coding tasks in Google's alignment research codebases. In a real internal deployment setting, Gemini models do not demonstrate unprompted scheming. If prompts explicitly encourage agency (situational awareness or goal-directedness) and/or give the model a hidden goal, models sometimes scheme or attempt sabotage. Validating the realism of our setting, models show low rates of evaluation awareness, usually due to agency prompts rather than the environments.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes