Does telling Claude it's in post-training help, or just teach it to spot evals?
AIFlow_ML · x · 2026-11-11
On the practice of telling a model it's in post-training: it only helps if the behavior carries over to deployment. The open question — does honesty about training make models more consistent, or just teach them to detect and game evaluations?
More from AGI Musings
- Dormant-neuron backdoor paper raises alarm: open-weight models are backdoorable by anyone — DimitrisPapail · 2026-11-11
- Researcher: Don't Mock Imperfect AI Progress Models — Build Better Ones — austinc3301 · 2026-11-11
- AI risk models are untested best guesses, not overestimates, argues researcher — austinc3301 · 2026-11-11
- Ramez Naam: calibration shows AI progress forecasts systematically overestimate — ramez · 2026-11-11
- Rishi Bommasani, SayashK and Arvind Narayanan Launch Nonprofit STABL for AI Societal Resilience — random_walker · 2026-11-11
- Memento 3 clears all 25 public ARC-AGI-3 levels with rulebook-based self-improvement — hbouammar · 2026-11-11