Similarly, cars today are far superior to old cars in terms of safety, and the gains that have been made on the engine side of things are nothing short of incredible. Every modern car is essentially a supercar by the standards of the 90s in terms of oomph per unit of displacement. The problem is that all of the systems have been coupled together, often needlessly, in order to improve telemetry and capture a bigger share of the used market. It's hostile towards the end user.

There's no question that the level of quality today is higher, especially where it matters. It's just that value extraction eventually turns hostile towards consumers in the absence of real competition and the need for endless growth.

Being unable to state the solution of a problem in closed form doesn't prevent solutions from existing.

The sharp edges are usually pointing the package manager at a repo (generally an official expansion) that lets you install the necessary binary.

Full disclosure, this is one of my pie-in-sky ideas that I've been letting AI loose on with only top down direction from me. I'm usually fairly hands-on even with the model in the loop, but this is an exception, because a geometry kernel is frankly beyond my ability to write solo (and I say that as someone with a reasonably strong math background). The gamble has always been that if a current model can produce "works, but crap under the hood", future models will be able to clean it up to "works, and is solid under the hood".

I'll push everything up by the weekend and drop you a line.

I'm not sure what others are doing that they're getting such different results, but I'll take Codex every day of the week.

Even our large language models have an implicit embodiment in the domain of text (and more recently, multimodal inputs). That seems sufficient for certain things, and insufficient for others. I suspect that AGI that does everything a human can do eventually turns out to be fairly analogous to humans in terms of sensory input and domain output, even if the scale is radically different (e.g. thousands of robots uploading (touch, sight, audio, smell, etc.) sensory data to a single model, and each being actuated individually).