Re:On Sleeper Agent LLMs
by almoehi on Friday January 12, 2024 @10:48PM
(#38977178)
Sounds like LLMs having their SQL injection equivalent moment.
I’d also say this described phenomenon isn’t new - except for it’s applied context: it’s essentially disinformation - a well known technique used by military since decades. Except now we hack LLM agents instead of real people’s minds.
I’d also say this described phenomenon isn’t new - except for it’s applied context: it’s essentially disinformation - a well known technique used by military since decades. Except now we hack LLM agents instead of real people’s minds.
Nonetheless interesting to watch.