What are self-replicating ‘AI worms’, and why is Anthropic worried about them?
The tech company says successful AI worms need more capability on less powerful devices, but current trends make that feasible by the end of the year Warnings about what artificial intelligence might do in the future – together with alarming reports of what it has gotten up to already – are being issued so quickly that even security experts have difficulty triaging what to worry about. Yet a…
Self-replicating AI worms are malicious AI programs that can autonomously spread through internet-connected devices, such as smart televisions. These worms are a concern for companies like Anthropic because they can function on less powerful devices as computing power increases. The Anthropic team created an AI worm that spread among 15 televisions and demonstrated that this type of threat could become feasible by the end of the year.
While the damage caused by AI worms could be significant, similar to other destructive malware in the past, the researchers emphasized that basic security measures, like strong passwords and two-factor authentication, could mitigate the risk. However, some experts in cybersecurity and government oversight believe that the threat of AI worms should be taken more seriously and that greater action is needed to address this emerging danger.
Written by urgent.news from Guardian Business's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
