I don't know if I want to create an ad-hoc list of permissions. What I would like would be something like take a snapshot of my current workspace in a VM. Run claude there and let it go wild. After the end of the session, kill the box. The only downside is potentially syncing the claude sessions/projects. But I don't think that'd be too difficult.
> Bubblewrap and Docker are not hardened security isolation mechanisms, but that's okay with me.
Edit to add: my understanding is the major flaw in this approach is potential bugs in Linux kernel that would allow sandbox escape. Would appreciate your insight if there are some easier/more probable attack vectors.
In the UK we move forward at 1am and they go backward at 2am. Doing it at midnight adds the extra complexity that now the day is different. Doing it in the early morning doesn't change the day.
My guess is that in the US they do the same but shifted by one.
It's hard to pin point what creativity is. But in your example, the more creative thing was really coming up with the scenario of pigeons selling balconies as real state. What followed was just applying usual tropes for that sort of joke on the subject matter. I feel like LLMs are not very good at coming up with something novel. I'm not even sure they are capable of that. It's not as if coming up with something novel is easy for humans either.
Plus, a lot of people are generating hallucination and believing that is invoking creativity. I contend the outputs/generations are junk, but human creativity and human comprehension step in and create meaning to the hallucination.
They can't because they aren't, right? That's the whole point of having them not expiring. Until you used them, you can still get your money back in some situations.
reply