tehfishman

@tehfishman@ioc.exchange

"professional" peanut gallery for security stuff

Replying to @Viss@mastodon.social

@Viss @neurovagrant I can't find it right now, but I recently read more serious (than a shitpost YouTuber) research on this that amounted to: LLMs don't actually have a sense of who's talking in a conversation, and the only reason they appear to be capable of that is mostly down to speaking style in the training data. You can break guardrails if you copy their speaking style for long enough that they forget who is who.