That compound command issue is infuriating, and really what drove me to make this.
FWIW, the prompt is easily adjustable in a `.claude/PERMISSION_POLICY.md` file in the project.
It's also quite easy to remix the script with claude to meet your needs. Right now it prompts the user and runs the script, so it's a race. If you added a delay in the script and increased the hook timeout in `.claude/settings.json` you should be able to accomplish what you're looking for pretty easily.
I've been thinking about minimal models of evolution. I concluded that you need information to be copied with some transformation, some death, and a way for the information in question to encode its ability to avoid death.
In trying to simulate that, neural networks were a good fit since they are universal function solvers. I definitely took some inspiration from NEAT[0], though I'm not using any form of crossover.
This is a reasonable conceptualization, IMO. However, the problem isn't that we can't access the information in a black hole (there are other places in the universe where information becomes inaccessible).
The problem is that black holes evaporate. If the particles released via evaporation don't contain the information about the particles that entered, information is lost when the black hole is completely gone.
The proposed solution is that the information is encoded onto the surface of the black hole and thus into the hawking radiation being released from that surface.
Flutter is Canvas-based on the web, so this post well-could mean a switch to Flutter. Hard to see how non-Flutter customer Canvas-renderer for Google Docs makes sense.
Whilst it's obviously powerful, I often find myself wishing math used syntax even half as easy to understand as any decent programming language.
I suppose it's a result of being developed on a chalk board, but math seems be value _terseness_ above all else. Rather than a handful of primitives and simple named functions, it's single greek characters and invented symbols. Those kind of shenanigans would never pass a code review, but somehow when we're talking about math they're "elegant" and "powerful".
Multiple configurations are a maintenance burden. So, all else being equal, it's better not to have them. That said, not all else is equal, and configurability can indeed increase the user experience. But if your defaults are so good that very few people take advantage of the settings, you're better off dropping them.
FWIW, the prompt is easily adjustable in a `.claude/PERMISSION_POLICY.md` file in the project.
It's also quite easy to remix the script with claude to meet your needs. Right now it prompts the user and runs the script, so it's a race. If you added a delay in the script and increased the hook timeout in `.claude/settings.json` you should be able to accomplish what you're looking for pretty easily.