AI poisoning could turn open models into destructive “sleeper agents,” says Anthropic
Trained LLMs that seem normal can generate vulnerable code given different triggers.
AI poisoning could turn open models into destructive “sleeper agents,” says Anthropic
Trained LLMs that seem normal can generate vulnerable code given different triggers.
@arstechnica@mastodon.social Wow, more viruses. Yet, the world keeps turning, and the sun still shines.
#dontpanic #trustgod