AI poisoning could turn open models into destructive “sleeper agents,” says Anthropic

AI poisoning could turn open models into destructive “sleeper agents,” says Anthropic

Trained LLMs that seem normal can generate vulnerable code given different triggers.

https://arstechnica.com/information-technology/2024/01/ai-poisoning-could-turn-open-models-into-destructive-sleeper-agents-says-anthropic/?utm_brand=arstechnica&utm_social-type=owned&utm_source=mastodon&utm_medium=social