External evaluators find flaws in OpenAI's AI monitoring system in pilot review

·1h ago
Share:PostShare

Oct 22 : AI safety evaluators METR and Redwood Research found several new vulnerabilities in OpenAI's internal system, including an exploit agents could have used to keep hundreds of their actions from being monitored, in a pilot review earlier this year. The exercise, conducted from July 21 to August 11, gave

C

Channel Newsasia

Original source

Read full story

Related Stories

Business1h ago

AI safety group METR finds flaws in OpenAI’s internal monitoring system

Oct 22 : AI safety research group METR said on Thursday a pilot exercise to stress-test OpenAI’s internal monitoring system uncovered several new vulnerabilities, including an exploit that AI agents could have used to keep hundreds of their recent actions from being monitored. OpenAI has since said all vuln

CChannel Newsasia
Business1h ago

Cable capacity emerges as bottleneck for AI data centres, Nexans says

Oct 22 : Cable production capacity is emerging as a bottleneck for AI-driven data centre construction, Nexans' finance chief said, as demand rises faster than the industry's ability to expand manufacturing capacity. Global cable capacity is tight and building a new cross-linked polyethylene (XLPE) cable produc

CChannel Newsasia

Headlines and briefs on this site are for information only. Always verify details on the original source or live status page.

Read Disclaimer