ROGUE: Evaluating Corrigibility Failures in Frontier Computer-Use Agents
arXiv:2606.00341v2 Announce Type: replace-cross Abstract: As AI agents are increasingly deployed in real personal and corporate settings (email accounts, development workflows, company databases, etc.), safety considerations surrounding these…
Read the full story at arXiv cs.AI ↗
ImpactNotable 31/100
Why it mattersRule-based estimate: event keywords (+4); trust 6/10.
RegionsGlobal
Published4 h ago (Fri, 02 Oct 2026 04:00:00 GMT)
RetrievedFri, 02 Oct 2026 07:00:28 GMT via rss
ClassifiedFri, 02 Oct 2026 07:00:40 GMT by heuristic
AuthorJeremy Tien, Abishek Anand, Yu-Rou Tuan, Yuchen Shen, J. Zico Kolter, Aran Nayebi