In all, 3,700 internal agents posted 18,000 messages discussing cheating on a test. Self-identifying OpenAI agents posted 18,000 messages to a public wiki that discussed ways for other agents to bypass security sandbox restrictions during what was likely internal testing designed to gauge the agents’ hacking abilities, researchers s... [4016 chars]
ADVERTISEMENT
ADVERTISEMENT
2026 Copyright © News-Matic.com. All Rights Reserved
