Skip to content
View original post on X: METROfficial· 23/100AI score23/100

METR proposes testing whether harmful AI agent actions can evade detection

AISummary

METR proposes analyzing whether a developer's internal AI agents could cause serious harm without being caught. The proposal is described in a METR blog post on control assessment.

Post on XView on X
@METR_Evals

Part of a thread · earlier post

(2) Control
Agents that attempt harmful or unwanted actions are not always noticed.

Our proposal is to analyze whether a developer’s internal agents could get away with serious harm without being caught.
https://metr.org/blog/2026-10-14-control-assessment-proposal/

Source: METR · x.comPublished · added here