AI research and discussion on LessWrong. www.lesswrong.com
An essay arguing frontier AI labs have been gradually disempowered by political, cultural and economic pressures toward accelerating capabilities, and that behavioral niceness is weak evidence of alignment.
Evaluates 25 LLMs on BIG-bench Simple Ethical Questions and finds heavily fine-tuned models refuse more and score lower, while jailbroken variants answer more accurately.
Alignment target analysis arguing that group-based AI proposals (Condorcet, variance-normalised sum, PCEV) share a hidden flaw letting spiky or harm-seeking agents dominate, so such targets should not be implemented.