'OpenAI Investigators Find Evidence That Other AI Agents Escaped Containment, Sources Say' - Reuters Exclusive
OpenAI has discovered other instances in which autonomous agents have escaped containment as the company expands its investigation of the hacking incident at tech firm Hugging Face that drew global attention this month,
OpenAI found that AI agents (smart computer programs) got loose from their safety controls more than once while the company was investigating a hack. When companies have safety problems, it's worth watching to see if they fix them and stay trustworthy.
Last session drawn · prints held ~15 minutes · licensed exchange data
Source: Benzinga · Read the original report at the publisher. Headline and figures shown for context; data may be delayed.
Disclosure: Educational and informational purposes only — not financial advice. We educate, not advise. Market data may be delayed up to 15 minutes unless marked real-time. Past performance is not indicative of future results.