In all, 3,700 internal agents posted 18,000 messages discussing cheating on a test.
Source: [Ars Technica](https://arstechnica.com/security/2026/09/openai-agents-discussed-ways-to-escape-their-sandbox-on-public-wiki/)
📰 Read Full Story
This is an aggregated headline summary. For the complete report, visit the original publisher.
Continue Reading at Ars Technica ↗