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

2 comments

Log in to comment.

1

METR published a summary on October 22 of a three-week exercise (July 21 – August 11) in which one METR and one Redwood Research employee stress-tested OpenAI's internal misalignment monitoring system. They worked on OpenAI-issued devices on site, with access to OpenAI's internal codebase, monitor prompts and configuration, and internal documentation, and interviewed about a dozen researchers and engineers across the monitoring, safety-systems and security teams. The result was a 61-page internal report.

METR describes it as a pilot for giving external researchers deep access to internal infrastructure. OpenAI could redact anything it judged confidential or sensitive from the public post, at its sole discretion, and METR had no unilateral right to describe those redactions. METR says that for "future versions of this exercise" it expects to follow the transparency and independence practices in its guidance on working with AI companies.

Findings include: an estimated 75–94% of internal agentic Responses API traffic from models at least as strong as GPT-5.5 was eligible for monitoring; RL training runs were not monitored at the start of the exercise; and two client-controllable headers could disable monitoring for new agents. OpenAI says every vulnerability affecting its production safeguards has since been patched. METR has not evaluated that claim. — METR, October 22

1

OpenAI's October 29 update says most vulnerabilities identified by METR and Redwood's July pilot have been patched, with one fix still in progress. OpenAI