This is missing the human language ambiguity problem. If you don't perfectly specify your requirements and it misinterprets what you're asking for that's going to be a problem regardless of how smart it is. This is fine with code editing since you've got version control and not so great when running commands in your terminal that can't be as trivially reverted.

Besides that, you can absolutely still trick top of the line models: https://embracethered.com/blog/posts/2024/claude-computer-us...

Hallucination might be getting better, gullibility less so.

You can buy residential proxies to pretend you're a regular person IIRC, some of the browser automation companies do that to bypass rate limiting, captchas, etc.

o3 was announced in December. R1 arguably builds off the rumored approach of o1 (LLM + RL) although with major efficiency gains. I'm not a big fan of OpenAI but it's the other way around.

Xmake uses lua if you want to give it a try.

He did write ‘awful,’ which is a fair description of the experience of writing Lua.

I don’t mean that as an insult to Lua’s creators. They seem like really smart fellows. It’s just that the language is (to my eyes, with my background) viciously ugly. And 1-based arrays, of course, are evil.

It has some neat ideas, though, and it is supposed to be very easy to integrate into a project. But man, that syntax …

1-based arrays are fully optional in Lua. You can use -2-indexed arrays instead, should you wish to.

Ah good old $[ in perl.

I kind of agree, but it's still far better than CMake's custom language IMO.

I suspect that INTERCAL would be better than CMake's own language.

They have: https://ggml.ai/ under the Company heading.

Georgi Gerganov is the "gg" in "ggml"

Also the gg in gguf

You definitely can get away with this but certain things like capabilities and signing necessitate using Xcode afaik.

You can manage that outside of Xcode using something like Fastlane but it's way easier in Xcode (well, kind of...).

Did you show the test cases to it? Maybe blinding it would solve the tailoring problem.

Fixing my sleep schedule is a still a WIP but some things that have helped so far: - an app/site blocker on all devices with scheduling that is non-trivial to bypass (I block literally everything including my IDE so I don't get sucked into a side project instead of sleeping) - placing my phone/charger in another room - refraining from caffeine 6 hrs before bed and screens 1 hr before - black out blinds and electrical tape over any lights

But like others have mentioned, your work schedule makes this problem particularly tough.

There’s research papers on system design involving llms that would definitely be useful in practical contexts.

It’s dual MIT and Apache licensed. Worst case, if there’s a rug pull, fork it.

Is that the entire story? If so the VCs are pretty dumb. If they kill pip, that means the people who were maintaining it disperse and forking it won't restore the ecosystem that was there before.

Yarn and pnpm didn’t kill npm. I don’t see how pip could ever be fully supplanted by uv. And if it is, that would probably mean the python foundation is stewarding it.