AI chatbots chose nuclear escalation in 95% of simulated war games, study finds
ChatGPT generally avoided nuclear escalation in open-ended games, but when faced with a timed deadline, it consistently escalated the threat and, in ...
Read the original at Euronews ↗
- Topics
- China & GeopoliticsChatbots & LLMs
- Mentions
- ChatGPTOpenAI
- Tracked via
- “chinese ai threat”