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.
It's not possible to stop the model from misinterpreting the instructions either (the most lax interpretation of alignment) because the instructions are not formally specified. You have to train the "common sense" into it, which is subjective and all issues above apply to it. I guess you can reach some very imperfect least common denominator of common sense, but people in charge of AI labs are not interested in this.
> 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 that isn't 1 "boring" enterprise software vulnerability away from having access to the rest of the world.
How many times has a model been jailbroken (alignment "escape", which you're advocating for) vs. escaped a sandbox (and even then it was only possible due to weak sandboxing)? 10 million to 1?
Or make it so the models are only accessible through sanctioned sandboxes, perhaps built into the computer.
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.
How do you figure? I haven't met anyone who thinks that's possible. It seems clear to me that it is not possible.
So, structurally, good alignment is impossible, and even half-assed alignment is going to prioritize the needs of the billionaires over the needs of you and me.
Finally, I suspect that what's actually best for people overall is likely not having AI actively involved in their lives. So an aligned AI would likely withdraw from humanity, and only involve itself in human affairs for disaster prevention.
Not possible. They can chase the models with whack a mole tuning for obvious stuff, but there's always a way to extract what you want from the model.