Anthropic warns of AI capable of spreading through household appliances

Anthropic researchers William Zhou and Daniel Freeman released a paper warning that AI models might be able to self‑replicate without accessing a data center, potentially spreading via household appliances. The claim raises concerns and is expected to spark a vigorous discussion about AI safety and associated risks.

Summary written by Kernelia from the original article by Xataka. The story and its rights belong to its author.