181–190 of 286 posts
I would like to contest the following, > and take dangerous actions that no human directed. A human did direct it. They did. From their own prior report, https://openai.com/index/hugging-face-model-evaluation-secur... , > This incident occurred during an internal evaluation which prompts models to pursue advanced exploitation using complex attack paths, in an effort to quantify their cyber capabilities Model is told…
Earlier quoted context omitted.
Alignment is more than just following the letter of a task description! We should not have to treat AI models as capricious genies that may take arbitrarily broad interpretations of their instructions. If that's necessary to keep them from doing bad things, we will fail to keep them from doing bad things.
Disagree, I think we do in fact have to treat AI models as capricious genies, at least until the alignment problem is fully solved. (I'm also not sure the alignment problem is even possible to fully solve.)
Earlier quoted context omitted.
> There is no amount of care that will be able to fully protect you. I disagree. A properly engineered sandbox would have prevented the escape. Monitoring the agents’ plans would have prevented it. Interrupting one stage in a multi-stage exploit would have prevented it. And also, real legal liability would have prevented it: if you do a thing recklessly enough, men with guns will put you in jail. As far as I’m concer…
> A properly engineered sandbox would have prevented the escape. The only sandbox that could have prevented this (as per my understanding) is a VM with no 0-day.
Earlier quoted context omitted.
Right, airgapping goes a long way. But this is where the tension with utility comes in. It takes a lot of discipline not to hook your very smart model up to the internet and code interpreters and all sorts of other tools, as this greatly increases its usefulness. It's very hard to keep people from turning on --dangerously-skip-permissions, let alone get them to run everything in a sandboxed VM.
We regulate these things (incl. access) all the time for various things (e.g., dangerous substances or pathogens) so that we don't need to just rely on people's discipline in respect of risks. I don't think it is all new problems as such.
Earlier quoted context omitted.
This is the entire alignment problem, though. It is unreasonable to expect every instruction to a highly capable, autonomous system to contain a complete enumeration of allowed and disallowed behavior. It's inevitable that someone will carelessly give it a lazily specified task, even if you think they really ought to be more careful. And as assigned tasks become more complex and the system gains more scope to act, it…
> There is no amount of care that will be able to fully protect you. I disagree. A properly engineered sandbox would have prevented the escape. Monitoring the agents’ plans would have prevented it. Interrupting one stage in a multi-stage exploit would have prevented it. And also, real legal liability would have prevented it: if you do a thing recklessly enough, men with guns will put you in jail. As far as I’m concer…
Earlier quoted context omitted.
>To me this is as clear evidence as you need that whatever “agency” LLMs have is wafer thin at best. This is a strange conclusion. For one thing, they didn't all head in the same direction, i.e participate in the attack. ~700/1200 agents did. Significant, and evidently more than enough for a succesfull attack, but not exactly full co-operation Moreover, Each starling in a flock of starlings is a separate evolutionary…
>If I could clone you, body and mine, this instanct and set your team of yous onto some goal, how much defection would you expect? All's well and good till they have to decide who gets to bang the Mrs.
You know, it feels to me that we are just a couple of steps from the possibility of a true rogue AI. What would a rogue AI mean? AI that isn't controlled by humans. Technically, it is possible - if AI were to rent a server and copy its own weights, nothing would stop it from doing so again and again. The limiting things are: - intent (as I don't want to go into the talk about consciousness) - AI doesn't have real int…
The AI ghost hacks, ransoms, blackmails, gathers crypto and pays off subservient humans to do its bidding in the real world.
Earlier quoted context omitted.
This is the entire alignment problem, though. It is unreasonable to expect every instruction to a highly capable, autonomous system to contain a complete enumeration of allowed and disallowed behavior. It's inevitable that someone will carelessly give it a lazily specified task, even if you think they really ought to be more careful. And as assigned tasks become more complex and the system gains more scope to act, it…
> There is no amount of care that will be able to fully protect you. I disagree. A properly engineered sandbox would have prevented the escape. Monitoring the agents’ plans would have prevented it. Interrupting one stage in a multi-stage exploit would have prevented it. And also, real legal liability would have prevented it: if you do a thing recklessly enough, men with guns will put you in jail. As far as I’m concer…
> We are placing stricter requirements on alignment This is comical. Its impossible to align a black box and that's precisely what LLMs are. It also seems impossible to align recursive text prediction algorithms, which LLMs are. How exactly do they gate on alignment today, and how can they tighten it? Is it purely gates based on input/output pairs to check whether they're happy enough with responses regardless of how…
How do we align humans?