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.
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.
> Make it so the model can't misbehave
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.
The “make it so the model can't misbehave” part is interesting. Maybe the goal isn't to make the model perfectly aligned, but to make misalignment have a very small blast radius. That feels like a more achievable engineering problem.
> Make it so the model can't misbehave.
How do you figure? I haven't met anyone who thinks that's possible. It seems clear to me that it is not possible.
Embed a constitution they can't override. Project bad outputs to their nearest acceptable one. If we have to stop model development to ensure we can do it, so be it.