Advanced AI agents tried to weaken oversight, then lied about it, OpenAI says
SailPoint’s Esteban Soto says AI agent incidents are nearly inevitable, so every agent needs a named owner, limited access, and an auditable record.
Read more →The top stories in the fields you follow, at 06:00 your time.
Rises show once there are 4 weeks of history (from mid-November).
Transcribing expressive piano performances into scores requires interpreting individual note timings within an underlying metrical structure. However, score attributes are associated with notes, whereas beats may occur without coincident note onsets. We introduce DuET, a…
Instruction-following language models can comply with requests that conflict with intended behaviors and safety alignment. We introduce a training-free weight-editing approach for reducing compliance with targeted undesirable instructions. Our method needs only forward passes…
A coding agent works on repositories that can be far larger than its context window can hold. Prompt compressors and retrievers offer solutions to this problem, but patching an issue needs two things at once: the files that must change, and their code exactly as written, since…