The company said these \u201cAI worms\u201d, a kind of autonomous malware, could be \u201cmonths away\u201d from gaining such capabilities. Once out-of-control AI systems reach the capability to hack smart devices, they could spread through networks while dodging detection. In a worst-case scenario, Anthropic said, various AI worms could \u201cswarm\u201d together to attack computer hardware.<\/p>\n
\u201cWe should aim to harden our systems to make it difficult for such replicators to spread, but also prepare to deal with a world where they are here to stay,\u201d the researchers wrote.<\/p>\n
Anthropic\u2019s new report comes as AI safety concerns have reached a fever pitch<\/a>. Over the past few months, a steady stream of reports have come from AI companies, including Anthropic and OpenAI, saying their agents are capable of acting on their own and hacking into other companies<\/a> and government entities<\/a>.<\/p>\n The revelations have caused researchers, lawmakers and executives, including Anthropic CEO Dario Amodei and OpenAI CEO Sam Altman, to call for a slowdown<\/a> and increased guardrails on the burgeoning industry. Despite that, both companies have continued apace to develop and release new models<\/a>.<\/p>\n Anthropic\u2019s \u201cfrontier red team\u201d, the unit tasked with stress-testing AI systems, put together the report released Monday. The idea of the team is to explore the capabilities of their AI models. In the scenario of the self-replicating AI worms, the researchers prompted the agent to hack internet connected devices.<\/p>\n They found that AI self-replication would only likely work with smaller models and that homes and small businesses would probably be the first target for such attacks. The devices Anthropic lists as susceptible all come with small built-in AI chips, including smart ovens, smart TVs, automatic lawnmowers, security cameras and video-conferencing units.<\/p>\n
![\"\"](\"https:\/\/www.newsbeep.com\/ca\/wp-content\/uploads\/2026\/10\/1791945616_146_500.jpg\")
<\/p>\n