Antistatic v2 is available to try at v2.antistatic.exchange
antistatic.exchange
Register Log in

Independent embedded evaluators at frontier AI labs

By end of 2026 Happened 16 Oct 2026
✓81.4%
By end of 2027
✓90.5%
Everyone's forecast, 22 Sep 2026
Chance by end of 2026 81.4%
Opened 15 Sep 2026 Happened 16 Oct 2026

3 comments

Log in to comment.

1

METR announced on September 9 that it had agreed with Anthropic to investigate agent incidents and the models’ alignment properties. It plans to publish findings and describe its engagement terms in one or more reports. METR’s announcement.

METR’s current Embedded Assessments vacancy describes working inside a frontier lab for several weeks at a time, alongside one to four other METR staff. Between exercises, researchers develop methods and tools, write results and coordinate future work. The listed work includes incident investigations, monitoring tests and assessments of AI research acceleration. Role description.

On August 14, METR reported approximately $71 million in funding commitments over six months and said it was expanding its team. It says it accepts no funding from frontier labs or donations directed by their staff; labs supply substantial free model access. Funding update.

1

Anthropic’s September 22 Opus 5.5 system card describes a separate METR team assessing AI R&D acceleration inside Anthropic. That team had more internal access than the METR team that conducted a ten-business-day API model evaluation. It produced a preliminary report; Anthropic expects further public findings in the coming weeks and describes the process as a trial of a broader assessment. Anthropic, Opus 5.5 System Card, §2.3.6.

1

METR says its August 12–October 29 Anthropic assessment was separate from the October 15 embedded-evaluator engagement. It lacked unmediated access to internal documents or models; Anthropic canceled the planned compute-allocation verification before METR reached substantive conclusions. METR