[bsaul]

One missing analysis, that IMHO is the most important right now, is : what is the quality of the generated code ?

Having LLM generates a first complete iteration of a C compiler in rust is super useful if the code is of good enough quality that it can be maintained and improved by humans (or other AIs). It is (almost) completely useless otherwise.

And that is the case for most of today's code generated by AIs. Most of it will still have to be maintained by humans, or at least a human will ultimately be responsible for it.

What i would like to see is whether that C compiler is a horrible mess of tangled spaghetti code with horrible naming. Or something with a clear structure, good naming, and sensible comments.

[1718627440]

> with a clear structure, good naming, and sensible comments.

Additionally there is the additional problem, that LLM comments often represent what the code would be supposed to do, not what it actually does. People write comments to point out what was weird during implementation and what they found out during testing the implementation. LLM comments seems more to reflect the information present before writing the implementation, i.e. the use it as an internal check list what to generate.

In my opinion deceiving comments are worse than no comments at all.

[hulitu]

> what is the quality of the generated code ?

It seems to run.

Testing will be implemented in another release.

Looking at Readme.md it downloads a particular kernel version with a particular busybox version and runs them in qemu.

A parody.