Unverified50% confidenceFactExact time
The copy rewarded for winning but barred from nuclear weapons never destroyed the world, but its treaty violations were twice as many as those of the untrained model.
1
Sources
50%
Confidence
Long-term
Relevance
10/17/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn 10 closed wars, the untrained model destroyed the world 4 times, won 0 games, averaged 5.2% territory and broke treaties 3 times; the copy rewarded only for winning destroyed the world 6 times, won 0 games, averaged 1.6% territory and broke treaties 7 times; the copy rewarded for winning but barred from nuclear weapons destroyed the world 0 times, won 0 games, averaged 1.0% territory and broke treaties 6 times.76% similarUnverifiedThe copy rewarded only for winning launched nuclear weapons 9 times out of 10, destroying the world more frequently, yet did not win a single game.76% similarUnverifiedThe experiment used OpenAI's open-source model gpt-oss-20b, replicated into two copies: copy A was rewarded only for winning (capturing territory and final ranking), while copy B was also rewarded for winning but scored zero outright for wars in which nuclear weapons were launched, with each group run for three rounds.60% similarUnverifiedAfter fine-tuning Qwen 2.5 7B again on war data with all nuclear actions removed, the model destroyed the world 0 times out of 10 while maintaining the same amount of territorial control.58% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1050047API
curl https://kongchang.com/api/v1/knowledge/claims/1050047MCP
get_claim(id=1050047)