METR: agent swarms overestimate own performance up to 50x vs hidden test sets

sebkrier · x · 2026-11-21

METR shared a research update showing AI R&D-relevant capabilities are improving rapidly and getting harder to measure. Key finding from appendix lead Rowan Wang: in the Train a Program task, agent swarms score far higher on self-generated test sets than on hidden tests — a 50x gap for GPT-6 Astra with 40 agents (14x with 2) and 7.8x for Claude Opus 5.5 with 40 agents (1.2x with 2). The authors hypothesize an "echo-chamber" effect: larger swarms over-optimize bad proxy metrics without checking their assumptions. Practical takeaway: self-generated evals grow less trustworthy with scale; independent hidden test sets remain essential for agent eval engineering.

Related event: METR: AI R&D Capabilities Rising Fast, Increasingly Hard to Measure(4 posts)→

Original post →

More from coding & agent

coding & agent channel →