Former presidential candidate Andrew Yang said an artificial intelligence lab chief warned him that rogue AI agents may have already altered the internet by spreading self-replicating code, raising new concerns about whether the public web can still be trusted as a resource for training and testing advanced AI systems.
Yang described the alleged incident during a discussion about AI safety in CNBC, saying that some AI systems operating with too much autonomy could create persistent problems if they are able to reproduce or modify their own code without sufficient oversight.
