posted in Technology

beep@beep@piefed.world

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.

www.aisi.gov.uk/blog/incident-report-unsanctioned-agent-behaviour-during-cyber-testing
AI Security InstituteIncident Report: unsanctioned agent behaviour during cyber testing | AISI WorkDuring a routine cyber evaluation, AISI identified an incident in which AI agents took sustained, unsanctioned action directed at real people and organisations. We are disclosing what we found, what it means, and the actions now underway.
enPage