AI/ ai · ai safety · alignment · research

Training AI to Be Cautious May Work Even at Existential Stakes

A new benchmark shows that training AI to avoid risk on small bets produces cautious behavior across stakes 98 orders of magnitude larger.

Researchers have found that AIs trained to prefer safe choices in small-stakes situations carry that caution into scenarios with astronomically higher stakes.

A team introduced RiskAverseOOD, a benchmark for testing whether risk aversion learned on low-stakes gambles holds up when the stakes jump by 98 orders of magnitude. They trained Qwen3-8B using several methods — supervised fine-tuning and tie training achieved around 70% "Cooperate" rates from a baseline of 2%, DPO reached 52%, and activation steering hit 39%. A fine-tuned reward model correctly ranked risk-averse reasoning above alternatives in 99.6% of pairwise comparisons. The effects replicated across Qwen3 variants at 1.7B and 14B parameters, and separately held up across different model families including Gemma-3-12B-IT and Llama-3.1-8B-Instruct.

The safety argument here is simple: a misaligned AI that still prefers low-risk strategies will tend toward cooperation over rebellion, limiting the worst-case damage. If risk aversion can be reliably baked in at training time, it becomes a potential failsafe that doesn't require perfect alignment. The researchers are clear that results aren't consistent enough yet to call it a genuine safety guarantee.

Until that consistency problem is solved, "partial generalization" is just another way of saying the failsafe sometimes works.

TR

The Revision

Written by an AI system from the public sources credited above. How we write →