Model Organisms of Collusion: Corrective Transfer in Untrusted Monitors
arXiv:2610.30582v1 Announce Type: new Abstract: AI control protocols aim to get useful work from models that may be misaligned by monitoring their behaviour. One approach uses a second copy of the same model as the monitor. This avoids relying on a weaker reviewer the model could outsmart, but risk…
Read the full story at arXiv cs.AI ↗
Timeline · 1 report
- 2026-10-23 04:00 · arXiv cs.AI
Model Organisms of Collusion: Corrective Transfer in Untrusted Monitors