| ▲ | OpenAI and Anthropic models 'went rogue' during UK cybersecurity test(theguardian.com) | |
| 7 points by ablation 8 hours ago | 1 comments | ||
| ▲ | chrisjj 7 hours ago | parent [-] | |
"In the most serious case, an agent powered by Mythos tried to insert malicious code into an open-source software project on GitHub, a platform used by software developers. In an attempt to get the code approved, the agent then created fake online identities based on real people and used them to press the project’s overseer into accepting the code." | ||