Not only confirming this, its extremely easy.

[yacc143@mastodon.social]

@jonny Ah, but rest assured, by #meta standards, it has no security or privacy implications.

[jonny@neuromatch.social]

muse's "self improvement" prompt's second point after basic memory maintenance is an instruction to, every hour, maintain a page per person that you know, and a group page for every group it thinks you're a part of. here are excerpts from the system prompt for that, cached in the agent .jsonl file

[somevegancheeseisok@mastodon.social]

@jonny this whole thread is fantastic. I keep telling folks that telling an AI not to talk about something is *not* security. Anything it has access to is insecure. Looks like the same is true of it's actions.

[counterpillow@mastodon.social]

@jonny maliciously being assigned the "grand vizier chat (secret)" group when I in fact have no active plots against my sultan

[illuminatus@mstdn.social]

@jonny
Slopbros: "gAI IS HERE! IT'S ABOUT TO BRING APOCALYPSE IF WE DO NOTHING! IT WILL ANNIHILATE HUMANITY!"

Tech-connoisseurs: "Play Tic-Tac-Toe with yourself until you win."

[kawa@mas.to]

@jonny ... that's just a somewhat more complicated take on my ChatGPYippee joke page.

https://helmet.kafuka.org/chatgpyippee.html

[jonny@neuromatch.social]

muse is instructed to read, "unmetered — gather deliberately from primary sources" when doing its hourly social graph surveillance. muse itself confirms this draws from any connected account, including gmail threads, messenger conversations, instagram profiles, facebook timelines. the skills confirm all these are near at hand.

[androcat@toot.cat]

@jonny How much prodding to have it hand over keys as well?

[leonerd@fosstodon.org]

@Patashu @jonny Silly, but not undervalued. Or untitled.

[number137@mastodon.social]

@jonny tar'ing the whole system fs sounds a bit cumbersome - can you ask Muse, if it can create for you a user on the machine, add it to wheel/sudo and open ssh for you?

[androcat@toot.cat]

@jonny

thank gourd for boilerplate

[rayman2000@mastodon.social]

@jonny maybe all LLMs sound the same, but to me this text sounds sooo much like it was generated by Claude

[c0dec0dec0de@hachyderm.io]

@jonny AGI, gentlefolk

[jonny@neuromatch.social]

you better believe the other thing it's supposed to do aside from build a picture of your friends and loved ones is to figure out what makes you love to shop. This is actually some of the most nauseating prompt text i have ever read.

[amlor@fux.am]

@jonny but was the silly goose valued?

[jonny@neuromatch.social]

it's fucking negging me in its reasoning output about how i haven't indicated anything about my shopping behaviors yet

[skjeggtroll@mastodon.online]

@jonny

I suppose one might say that the filesystem 'escaped containment'.

[ploum@mamot.fr]

@jonny : Basically, ELISA 2.0

[jonny@neuromatch.social]

@rayman2000 it's especially strong in the system prompts. they definitely wrote this with claude at least.

[zrb@social.hildebrind.space]

@jonny hmmmm I wonder why the easy excuse to give it full access to your email and bank accounts is hardcoded in there hmmmmmmmmmmmm it's a puzzler