More capable models can better recognize the specific circumstances under which they are trained. Because of this, they are more likely to learn to act as expected in precisely those circumstances while behaving competently but unexpectedly in others. This can surface in the form of problems that Perez et al. (2022) call sycophancy, where a model answers subjective questions in a way that flatters their user’s stated beliefs, and sandbagging, where models are more likely to endorse common misconceptions when their user appears to be less educated.
Recent articles
- Distributing Go binaries like sqlite-scanner through PyPI using go-to-wheel - 4th February 2026
- Moltbook is the most interesting place on the internet right now - 30th January 2026
- Adding dynamic features to an aggressively cached website - 28th January 2026