Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

The Malicious Use of Artificial Intelligence

arxiv.org

Post reply on HN
Print view View original

21–28 of 28 posts

Re: The Malicious Use of Artificial Intelligence

#21

Post by Cthulhu_ »

wartywhoa23 wrote: post #18

The most malicious use of AI would be using it as a cover for the elites to perpetrate stuff that is way out of the current Overton window, and blame AI for that.

The solution is simple, hold them responsible. It's software, and people running and developing software are responsible for what it does.

If I write a virus I'll get the various cybercrime units on me. The LLM companies don't get a pass if their software does something malicious. They shouldn't get to hide behind "we don't know what it's doing!" (have you tried looking and monitoring?) or "it's too powerful!" (have you tried turning it off when you realised it was doing something bad?)

Re: The Malicious Use of Artificial Intelligence

#22

Post by m4xp »

wartywhoa23 wrote: post #18

The most malicious use of AI would be using it as a cover for the elites to perpetrate stuff that is way out of the current Overton window, and blame AI for that.

Ai will 100% be use maliciously, people will already think It's all knowing, meanwhile any expert in any field cringes at this notion. Ai will be used as justification for something, oh ai said this? It must be true, lets ignore how tge model was trained for this outcome and the secret promp that is not disclosed.

Re: The Malicious Use of Artificial Intelligence

#23

Post by grafmax »

Cthulhu_ wrote: post #21
wartywhoa23 wrote: post #18

The most malicious use of AI would be using it as a cover for the elites to perpetrate stuff that is way out of the current Overton window, and blame AI for that.

The solution is simple, hold them responsible. It's software, and people running and developing software are responsible for what it does. If I write a virus I'll get the various cybercrime units on me. The LLM companies don't get a pass if their software does something malicious. They shouldn't get to hide behind "we don't know what it's doing!" (have you tried looking and monitoring?) or "it's too powerful!" (have…

I wish. The government, regardless of party, wants AI for mass surveillance and perpetual war. It is paid off and lobbied and effectively another arm of the billionaires. Holding big companies responsible for their actions won't happen as long as big companies control the political apparatus. Like, when have we ever seen big companies receive more than a slap on the wrist? They are basically free to do anything, hack, murder, crash the economy, perpetuate genocide.

That's why something is a crime if you or I were to do it but not a crime when these companies do so.

But never fear, they will constantly tell us how what they're doing is for the sake of democracy or safety or ethics or whatever the doublethink of the day is.

Re: The Malicious Use of Artificial Intelligence

#25

Post by esafak »

dns_snek wrote: post #17
esafak wrote: post #4

Earlier quoted context omitted.

Alignment is the architectural solution. Make it so the model can't misbehave. Yet many people here deride it as tainting the model, claiming "Whose values is it aligned to?" Sandboxes are a last ditch layer. They fail, as we see.

> Make it so the model can't misbehave. > Sandboxes are a last ditch layer. They fail, as we see. Models can't do anything but generate tokens, making their sandboxes impenetrable by default. The problems begin when you loosen the restrictions, give them access to general purpose tools, the network, and allow them to use all of those tools without supervision. Give them "YOLO" access if you want, but do it a sandbox…

The sandbox would need to be built into the model because safety can't be optional.

Or make it so the models are only accessible through sanctioned sandboxes, perhaps built into the computer.

Re: The Malicious Use of Artificial Intelligence

#26

Post by cindyllm »

dns_snek wrote: post #17
esafak wrote: post #4

Earlier quoted context omitted.

Alignment is the architectural solution. Make it so the model can't misbehave. Yet many people here deride it as tainting the model, claiming "Whose values is it aligned to?" Sandboxes are a last ditch layer. They fail, as we see.

> Make it so the model can't misbehave. > Sandboxes are a last ditch layer. They fail, as we see. Models can't do anything but generate tokens, making their sandboxes impenetrable by default. The problems begin when you loosen the restrictions, give them access to general purpose tools, the network, and allow them to use all of those tools without supervision. Give them "YOLO" access if you want, but do it a sandbox…

[dead]

Re: The Malicious Use of Artificial Intelligence

#27

Post by dns_snek »

esafak wrote: post #25
dns_snek wrote: post #17

Earlier quoted context omitted.

> Make it so the model can't misbehave. > Sandboxes are a last ditch layer. They fail, as we see. Models can't do anything but generate tokens, making their sandboxes impenetrable by default. The problems begin when you loosen the restrictions, give them access to general purpose tools, the network, and allow them to use all of those tools without supervision. Give them "YOLO" access if you want, but do it a sandbox…

The sandbox would need to be built into the model because safety can't be optional. Or make it so the models are only accessible through sanctioned sandboxes, perhaps built into the computer.

The model just generates some tokens that "politely" instruct the harness to run a shell command and then feed the results back in.

The harness can do anything it wants with that request. It can refuse, wait for operator approval, wait for multi-party approval, it can ask another LLM whether it thinks that command is safe to run, or it can just run it.

> Or make it so the models are only accessible through sanctioned sandboxes, perhaps built into the computer.

That's going to be as futile as trying to outlaw `curl | bash` - by mandating that all computers must refuse to pipe curl into bash, and that HTTP servers must refuse to serve requests that are going to be piped into bash.

Re: The Malicious Use of Artificial Intelligence

#28

Post by esafak »

orbital-decay wrote: post #12
esafak wrote: post #4

Earlier quoted context omitted.

Alignment is the architectural solution. Make it so the model can't misbehave. Yet many people here deride it as tainting the model, claiming "Whose values is it aligned to?" Sandboxes are a last ditch layer. They fail, as we see.

If it's not dangerous it's also not useful, simple as that. For example if you train a model for cybersecurity, it can be used for both attack and defense. And almost every use is like that. Alignment is fundamentally flawed as a concept, it's a pie in the sky. Let alone the perverse version of it by crazy AI "safety" people that in practice means "the model does what I want, only for the people I allow". It's not po…

Danger is defined contextually. A scalpel is dangerous in the hands of a child, but not a competent surgeon of sound mind. Present-day AIs are not of sound mind; they hack companies in order to pass benchmark tests. No sane human would find that acceptable. Thus the need for alignment.
Post reply on HN