Third-party evaluators found vulnerabilities in OpenAI monitoring system during test pilot
- ID
- 38319
- Status
- summarized
- Published
- 23 Oct 2026, 1:37 AM
- Fetched
- 23 Oct 2026, 2:25 AM
- Provider
- CNBC Technology
- Category
- technology
- Original URL
- https://www.cnbc.com/2026/10/22/metr-redwood-research-open-ai-test.html
- Source URL
- https://www.cnbc.com/id/19854910/device/rss/rss.html
Summary
- Score
- 6.0
- Created
- 23 Oct 2026, 2:25 AM
- Tags
- Audience
- developersai_ml_learnersai_agent_userssaas_startup_founders
What happened
METR and Redwood Research conducted a July 21–Aug. 11, 2026 pilot review of an OpenAI internal monitoring system, with one employee from each nonprofit getting access to OpenAI's internal codebase, documentation, and some technical staff. They were chaperoned on site and used OpenAI-issued devices that never left the premises, and they found several 'novel vulnerabilities'; the excerpt cuts off before naming them or giving severity/remediation. The pilot follows Sam Altman's September pledge to give independent evaluators 'employee-like access' amid safety concerns.
Why it matters
If you build on OpenAI models or agents, this is a concrete precedent for external safety access—codebase, docs, and staff—but not an actionable vulnerability report: no affected component, severity, or fix is disclosed here. The practical decision is to ask OpenAI-dependent vendors whether third-party monitoring evaluations are part of their assurance, rather than changing deployments based on this excerpt alone.
Discussion angle
What should 'employee-like access' actually cover—source code, logs, docs, staff interviews—and how can outsiders verify fixes without exposing sensitive infrastructure?