Replying to @prettygood@socially.drinkingatmy.computer
@prettygood first one, then the other.
@tehfishman@ioc.exchange
"professional" peanut gallery for security stuff
Replying to @prettygood@socially.drinkingatmy.computer
@prettygood first one, then the other.
Replying to @neurovagrant@masto.deoan.org
@neurovagrant @Viss yeah that's it. Really highlights how much of a clown show this all is
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.
Replying to @sarahtaber@mastodon.online
@sarahtaber this was a great watch with the context of having just watched Clarkson's Farm, a show about a wealthy farmer experiencing a series of bad things, many of which are due to his lack of experience as a farmer.