AI poisoning could turn open models into destructive “sleeper agents,” says Anthropic
Imagine downloading an open source AI language model, and all seems well at first, but it later turns malicious. On Friday, Anthropic—the maker of ChatGPT competitor Claude—released a research paper about AI "sleeper agent" large language models (LLM... [2498 chars]
Source: Ars Technica
