AI poisoning could turn open models into destructive “sleeper agents,” says Anthropic
Trained LLMs that seem normal can generate vulnerable code given different triggers.
You must log in or # to comment.
@arstechnica@mastodon.social 🤣🤣🤣🤣🤣😶🤣🤣🤣🤣🤣
I cannot wait for this crazy train to come off the rails.
I’ll be in my bunker deep in the Ozarks.
@arstechnica@mastodon.social Wow, more viruses. Yet, the world keeps turning, and the sun still shines.
#dontpanic #trustgod
