@rygorous With LLMs, lots of people don't read their own code (and probably lots of "writers" don't read their own writing and flood Amazon with books designed to make a few sales here and there).

I think there are more hot takes about the former than the latter, but probably mostly because it's more common (in terms of what someone might come across).

Looks like I spoke too soon about the AI not being superhuman. The current Azul world champion played against it and thinks it's better than him at higher difficulties, and a top 100 player played against it at default difficulty and thought it was better than him at default.

I should write a longer post about this. As someone who has a default of trying to have a better understanding of their project than most people would, going full vibe and understanding almost nothing was interesting.

@dynomight Sorry that was unclear! I used GPT-5.2 (seems to give you the most quota, and I did this in a way that used a ton of quota; even on the Pro plan, I had to throttle my usage) to generate code which ran on my laptop.

I'm sort of in the stone ages with my setup (codex plugin in vscode). I wouldn't recommend anyone use this because the plugin is so buggy, but it works ok enough if you want to queue up a bunch of work and occasionally check in on what it's doing.

I don't want to overstate the case — I saw someone vibe coded the same project and then declared programming was dead after they finished, but their bot loses to plain MCTS with a simple heuristic.

Mine was in the same state when I just had an LLM running in a loop with instructions to improve the result. At least for now, you have to apply some direction, but it turns out someone with no AI background can supply enough direction.

@tobinbaker @regehr @penguin42 Depends on what you want! I think I'd want, for all websites, JIT on, common image formats on, PDF off, for example, and I don't think you can do that?

I'm not sure if phone calls to watch can be enabled separately. I guess I can try to do it and see.