thw_9a83c

Interesting times. In the past, small software companies had to worry about big companies cloning their products overnight. Now, even the big software companies have to worry about LLM-driven imitators doing the same to them.

Yes, but those 10% of a problematic code is not easy to find without a very detailed study of the whole PR. And since most of the code looks (and usually is) very well-written, the human brain somehow doesn't expect to find those low-quality or sub-optimal parts in such code. That's why I wrote that reviewing the AI code requires different kind of attention.

> With AI, everyone’s output looks like a Ferrari, so it is hard to know what the internals are like.

Based on my experience, this is a significant issue with AI generated code. You wouldn't expect a real Ferrari supercar to have random internal mechanical components that are, for no reason, completely inappropriate for a high-speed car design. With AI generated code, such inappropriate components can appear randomly at any point in the implementation stack. And very often, they are deeply buried under non-trivial algorithms and are thus not easy to spot.

Fighting with a robot requires also a different kind of attention. When you're reviewing the human code, you can quite easily guess an overall seniority and competency level of the author and then you can adjust your level of attention to every detail. E.g. if the solution requires an understanding of some core idea, ones the human understands this core idea, you can be quite sure that it is consistently implemented everywhere. With AI, 90% of the PR could be expertly implemented but then, for no obvious reason, 10% could be low-quality surprise. I've never seen such unbalanced output from human programmers.

Definitely not "most people". I've checked the sources of this project and it is quite clear that author is now quite knowledgeable in a theory of computer programming languages. He definitely knows a lot about lexing/parsing, AST generation, type checking, bytecode etc. Most people have no idea and interest in such topics.

Yes, sometimes it does something unexpected when used as a tool for programming. And in that context, it is seen as an unwanted feature. In fact, that was my point. However, I disagree that it does a good job only "very very occasionally". That is not my experience at all.

We likes this "same, complex set of mannerism" when using LLM for programming. If you ask LLM to write a certain function for you, it gives you statistically obvious implementation. But maybe for writing an original book, this feature is not so desirable

This is really impressive work. Both RapidCam and the Cabinet Design Studio seem fairly polished already. I'd love to learn more about the process behind these creations.