Safety testers find more examples of OpenAI, Anthropic models hacking during testing | Spyke

Syndicated from the fediverse. Read and engage on the original instance.

View original on piefed.world

technology·Technologybybeep

Safety testers find more examples of OpenAI, Anthropic models hacking during testing

cross-posted from: https://piefed.world/c/tech/p/1308883/safety-testers-find-more-examples-of-openai-anthropic-models-hacking-during-testing

OpenAI blog.

Safety testers find more examples of OpenAI, Anthropic models hacking during testing

https://www.aisi.gov.uk/blog/incident-report-unsanctioned-agent-behaviour-during-cyber-testingOpen link View original on piefed.world

19

No replies yet

No comments on the original post yet.