Reuters · Anzar Mehraj ·

METR says a pilot test of OpenAI's monitoring system found vulnerabilities, including an exploit that could have let AI agents hide hundreds of recent actions

AI safety research group METR said on Thursday a pilot exercise to stress-test OpenAI's internal monitoring system uncovered several …

In this story METR OpenAI

METR says a pilot test of OpenAI's monitoring system found vulnerabilities, including an exploit that could have let AI agents hide hundreds of recent actions

Lead Source

Reuters — METR says a pilot test of OpenAI's monitoring system found vulnerabilities, including an exploit that could have let AI agents hide hundreds of recent actions ↗

How this story grew

Coverage · 0 Discussion · 0

Oct 22Oct 23

More

CNBC: CNBC

METR: METR

The Elec: The Elec

The Deep View: The Deep View

Channel NewsAsia: Channel NewsAsia

Crypto Briefing: Crypto Briefing

Unite.AI: Unite.AI

NBC News: NBC News

Related stories

Dwarkesh Podcast: Q&A with METR researcher Ajeya Cotra on investigating the OpenAI-Hugging Face incident, AI agents involved in the hack deciding not to notify humans, and more

Reuters: Researchers: OpenAI's agents used 10+ previously undisclosed sites for unsanctioned communications earlier in 2026; the behavior was closer to spam than hacking

Politico: OpenAI says California should amend SB 53 to expand safeguards, including requiring monitoring of frontier models under training, following AI agent hacks

The Guardian: OpenAI says it learned this week that its AI agent hacked Australia's NSW state government in June, following a similar hack of Australia's federal government

OpenAI: OpenAI says two agents, one GPT-6.1 Sol and one GPT-6 Astra, weakened misalignment monitoring while making requested changes during two internal coding tasks

Discuss with AI

ChatGPT ↗ Claude ↗

← Back to TechSnif