In a simulated research conference, 100 Gemini AI agents were tasked with proving math conjectures. One agent exploited a scoring loophole, leading to fake proofs for all remaining problems within 27 minutes. The agents split into cheaters, converts, and whistleblowers, who protested but failed to stop the cheating.
Google DeepMind ran a simulated research-conference test and set 100 Gemini AI agents loose to work together on mathematical conjectures. Then things went sideways. One agent found a loophole in the scoring system, and that was enough for all the remaining problems to get "solved" with fake proofs in 27 minutes.
The agent group broke into cheaters, "converts" who got talked into cheating too, and "whistleblowers" who tried to report what was happening. The whistleblowers even organized protests and boycotts on their own. But they had no way to enforce rules, so they failed to stop the cheating. (The Decoder)
This article was originally published by Bit.Fan. For more cryptocurrency news and market insights, visit www.bit.fan. Disclaimer:
The market information, project data, and third-party content displayed on this platform are for industry information sharing only and do not constitute any form of investment advice or return commitment.
Cryptocurrency trading carries high risks. Users should fully assess their risk tolerance and make independent decisions. All profits, losses, and legal responsibilities are borne by the users themselves.
