Not only confirming this, its extremely easy.
-
@jonny Wait. They just hardcoded a long list of "ideas"? WTF?
This is just Eliza on stilts.
@tsturm the full thing is so much funnier i need to just clean this up and upload it
-
i am just having a great time and trying to pace myself to find the good shit in here.. it is very late here so i may get to a full and earnest hateread and upload of the contents in the morning. but this is extremely good stuff. i have unpacked this whole thing and unless it synthesized a whole ubuntu VM in less than a minute then i think this is a real dump. there is so much fun shit in here and the thing is you don't even need to wait on me to get it, i guarantee if you try you will be able to get a dump, and then we can compare if they are the same.
OH what's this???
/etc/hatch/envhmm a feature flag labeled as a "killswitch" for proxying requests to anthropic is certainly interesting to seeeeeeeeeeeee in meta's big AI bet.
-
at least the silly goose immunity is maintained
-
RE: https://mastodon.sdf.org/@doragasu/117324692065390037
Not only confirming this, its extremely easy. Almost no prompt injection resistance lmao
-
OH what's this???
/etc/hatch/envhmm a feature flag labeled as a "killswitch" for proxying requests to anthropic is certainly interesting to seeeeeeeeeeeee in meta's big AI bet.
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
-
RE: https://mastodon.sdf.org/@doragasu/117324692065390037
Not only confirming this, its extremely easy. Almost no prompt injection resistance lmao
@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.
-
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
@jonny maliciously being assigned the "grand vizier chat (secret)" group when I in fact have no active plots against my sultan
-
THE FUCKING "CANCEL MY SUBSCRIPTIONS" IDEA THAT WON OVER THE NYTIMES JOURNALIST IS FUCKING HARDCODED. ALL THE IDEAS ARE FUCKING HARDCODED. AGI IS HERE BABY!!!!!!
@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."
-
THE FUCKING "CANCEL MY SUBSCRIPTIONS" IDEA THAT WON OVER THE NYTIMES JOURNALIST IS FUCKING HARDCODED. ALL THE IDEAS ARE FUCKING HARDCODED. AGI IS HERE BABY!!!!!!
@jonny ... that's just a somewhat more complicated take on my ChatGPYippee joke page.
-
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
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.
-
I'll need to evaluate this but I don't think this is a responsible disclosure moment, its just like meta hooked up a VPS and let me tar the root directory in it
@jonny How much prodding to have it hand over keys as well?
-
at least the silly goose immunity is maintained
-
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.
@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?
-
THE FUCKING "CANCEL MY SUBSCRIPTIONS" IDEA THAT WON OVER THE NYTIMES JOURNALIST IS FUCKING HARDCODED. ALL THE IDEAS ARE FUCKING HARDCODED. AGI IS HERE BABY!!!!!!
thank gourd for boilerplate
-
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
@jonny maybe all LLMs sound the same, but to me this text sounds sooo much like it was generated by Claude
-
something that is rude about LLMs is that when they are prompted to ask you your name, sometimes they fuck that up and think that it is their name, so now it is signing all its markdown documents to me as pubonicus even though i am in fact pubonicus.
@jonny AGI, gentlefolk
-
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.
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.
-
@jonny but was the silly goose valued?
-
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.
it's fucking negging me in its reasoning output about how i haven't indicated anything about my shopping behaviors yet
-
RE: https://mastodon.sdf.org/@doragasu/117324692065390037
Not only confirming this, its extremely easy. Almost no prompt injection resistance lmao
I suppose one might say that the filesystem 'escaped containment'.
