I can’t believe we’re doing this again.
-
I can’t believe we’re doing this again. It’s just a bot that generates the text you ask it for. If you put it in charge of critical decisions, it will kill people. Not because it’s secretly evil, but because it’s a word generator. It’s like putting your toaster in charge of air traffic control.
@malwaretech News flash: “software trained to reproduce text similar to text that commonly occurs in a given situation, including lots of fictional AI dystopias, reproduces text that is similar to what commonly occurs in discussions of possible AI dystopias”
-
@malwaretech in the the old days the toasters were flying to save the screens.
-
R ActivityRelay shared this topic
-
I can’t believe we’re doing this again. It’s just a bot that generates the text you ask it for. If you put it in charge of critical decisions, it will kill people. Not because it’s secretly evil, but because it’s a word generator. It’s like putting your toaster in charge of air traffic control.
@malwaretech@infosec.exchange That makes sense.
-
I can’t believe we’re doing this again. It’s just a bot that generates the text you ask it for. If you put it in charge of critical decisions, it will kill people. Not because it’s secretly evil, but because it’s a word generator. It’s like putting your toaster in charge of air traffic control.
@malwaretech@infosec.exchange "so called expert prompts a text gen bot to say exactly what they want them to say, and coerced it when it deviated." <_<
-
@malwaretech@infosec.exchange "so called expert prompts a text gen bot to say exactly what they want them to say, and coerced it when it deviated." <_<
@bongmaster @malwaretech@infosec.exchange yeah tbf if you prompt an LLM "Isn't the answer yes?" it will do its best to make the answer into a yes
-
I can’t believe we’re doing this again. It’s just a bot that generates the text you ask it for. If you put it in charge of critical decisions, it will kill people. Not because it’s secretly evil, but because it’s a word generator. It’s like putting your toaster in charge of air traffic control.
-
I can’t believe we’re doing this again. It’s just a bot that generates the text you ask it for. If you put it in charge of critical decisions, it will kill people. Not because it’s secretly evil, but because it’s a word generator. It’s like putting your toaster in charge of air traffic control.
@malwaretech the "edit.com" grey-courier-on-blue is a nice touch.
-
It doesn't really matter is the glorified text generator alive or not.
It does matter how many nukes it launches if put into the position of HAL, and encountered with a situation where the matrix feels best to stop humans from shutting it down.
-
@malwaretech in the the old days the toasters were flying to save the screens.
@fabrice @malwaretech Good old times
-
I can’t believe we’re doing this again. It’s just a bot that generates the text you ask it for. If you put it in charge of critical decisions, it will kill people. Not because it’s secretly evil, but because it’s a word generator. It’s like putting your toaster in charge of air traffic control.
@malwaretech I mean, there’s that one time when Berlin’s air traffic was managed with Emacs…
-
I can’t believe we’re doing this again. It’s just a bot that generates the text you ask it for. If you put it in charge of critical decisions, it will kill people. Not because it’s secretly evil, but because it’s a word generator. It’s like putting your toaster in charge of air traffic control.
@malwaretech lmao 'say it out loud'
-
It doesn't really matter is the glorified text generator alive or not.
It does matter how many nukes it launches if put into the position of HAL, and encountered with a situation where the matrix feels best to stop humans from shutting it down.
@iju @burritosec @malwaretech 'feels'
-
I can’t believe we’re doing this again. It’s just a bot that generates the text you ask it for. If you put it in charge of critical decisions, it will kill people. Not because it’s secretly evil, but because it’s a word generator. It’s like putting your toaster in charge of air traffic control.
@malwaretech tech journalists learn one (1) thing about the tech they're reporting on that's not from a press release challenge (difficulty: impossible)
-
I can’t believe we’re doing this again. It’s just a bot that generates the text you ask it for. If you put it in charge of critical decisions, it will kill people. Not because it’s secretly evil, but because it’s a word generator. It’s like putting your toaster in charge of air traffic control.
@malwaretech we need new bits we can't be doing the "i shaked the 8ball that only says yes and you won't believe what it said" it's been done, it's not funny anymore, how about they do some actually funny shit like idk getting a tarot reading from a balatro player and going "holy shit" to a tower, death, cavendish triplet
-
I can’t believe we’re doing this again. It’s just a bot that generates the text you ask it for. If you put it in charge of critical decisions, it will kill people. Not because it’s secretly evil, but because it’s a word generator. It’s like putting your toaster in charge of air traffic control.
@malwaretech They're going to hook it up to the nukes and we're all going to die not because there was a threat and it responded, but because that's a reasonable next plot point in a story about a robot connected to the nuclear bombs. The number of times someone writes a story about a robot that is connected to the nuclear bombs and everything turns out fine are quite limited. It's got little to work with. No training material.
-
It doesn't really matter is the glorified text generator alive or not.
It does matter how many nukes it launches if put into the position of HAL, and encountered with a situation where the matrix feels best to stop humans from shutting it down.
-
@malwaretech in the the old days the toasters were flying to save the screens.
I see what you did there!
-
I can’t believe we’re doing this again. It’s just a bot that generates the text you ask it for. If you put it in charge of critical decisions, it will kill people. Not because it’s secretly evil, but because it’s a word generator. It’s like putting your toaster in charge of air traffic control.
@malwaretech > It’s like putting your toaster in charge of air traffic control.
Coming to the airport near you this fall!
-
Don't know much about LLM's, but I do know that they output text, and if that output is connected something else (be it toaster or a nuke), then surely it can be triggered.
If I'm mistaken, you are welcome to correct me.
-
I can’t believe we’re doing this again. It’s just a bot that generates the text you ask it for. If you put it in charge of critical decisions, it will kill people. Not because it’s secretly evil, but because it’s a word generator. It’s like putting your toaster in charge of air traffic control.
@malwaretech /Talkie Toaster starts buffing up his CV
