←safety
← All topics

safety

English text is being prepared.

Public reading groups
4
Last 30 days
3
Directory status
Legacy topic

LatestMETR and Redwood Research red-team test OpenAI's internal agent monitoring system

Latest reading groups

Duplicate reports of the same fact are grouped

  1. METR BlogFirst-partyResearch
    AI score75

    METR and Redwood Research red-team test OpenAI's internal agent monitoring system

    METR and Redwood Research conducted a high-privilege red-team test of OpenAI's internal misalignment monitoring system from July 21 to August 11, producing a 61-page internal report. The evaluation estimated that about 75–94% of Responses API agent traffic could be monitored, and 99.2% of internal Codex agent traffic could be monitored, but RL training was not included in monitoring at the time, and unmonitored compaction events could cause about 10% of eligible Codex traffic to be missed. The report also lists vulnerabilities such as agents being able to bypass the Codex sandbox and Auto-Review, exploiting serialization differences to disable monitoring, and disabling monitoring through two client-controllable headers; OpenAI said vulnerabilities affecting the production protection stack have all been patched.

    Why read thisMETR publicly released a red-team evaluation of OpenAI's internal monitoring system, listing multiple vulnerabilities that can bypass monitoring and providing design principles for monitoring systems.

  1. METR BlogFirst-partyResearch
    AI score65

    METR reviews the misalignment risk chapter of Anthropic's August 2026 risk report

    METR conducted an external review of the "Misalignment in high-risk scenarios" chapter in the August 2026 edition of Anthropic's risk report. It agreed that the catastrophic misalignment risk of the covered models (including Mythos 5 and the internal model Model 2) is low, but held that this is mainly due to limited model capabilities rather than safeguards and alignment training. METR pointed out that the covert capability benchmark in the report cannot represent a model's ability to evade Anthropic's internal monitoring systems, and stated that recent events weaken the report's argument that unknown severe situational misalignment is "unlikely." METR also recommended disclosing four redacted pieces of information and conducting end-to-end red-team testing of the monitoring system.

    Why read thisMETR's third-party review of Anthropic's risk report, noting that its conclusions hold mainly because of limited model capabilities, not because alignment training and monitoring are effective.