Even in the original comic, that would have been appropriate, I think.

At one point the user linked to a rust-lang forum thread from 2016-2019 as evidence that Jai has “some of the tools to make the code language agnostic” or something like that. The thread started with a discussion of array-of-struct vs struct-of-array data layouts, which of course has nothing to do with making code “language agnostic.” The user also mentioned the coding influencer lunduke multiple times. So I think they are simply misinformed on a lot of points, and I doubt they’re in the closed beta for Jai.

(I read some of the comments simply because I had the same question you did. And, as it happens, the last post in the forum thread I mentioned was written by me, which was a funny surprise.)

Exactly: that’s tight feedback loops. Agents are also capable of reading docs and source code prior to generating new function calls, so they benefit from both of the solutions that I said people benefit from.

As an even more obvious example: students who put wrong answers on tests are “hallucinating” by the definition we apply to LLMs.

making the same mistakes

This is key, and I feel like a lot of people arguing about “hallucinations” don’t recognize it. Human memory is extremely fallible; we “hallucinate” wrong information all the time. If you’ve ever forgotten the name of a method, or whether that method even exists in the API you’re using, and started typing it out to see if your autocompleter recognizes it, you’ve just “hallucinated” in the same way an LLM would. The solution isn’t to require programmers to have perfect memory, but to have easily-searchable reference information (e.g. the ability to actually read or search through a class’s method signatures) and tight feedback loops (e.g. the autocompleter and other LSP/IDE features).

This seems like it doesn’t really answer OP’s question, which is specifically about the practical uses or misuses of LLMs, not about whether the “I” in “AI” is really “intelligent” or not.

I honestly don’t even understand the joke. Case-insensitive file names cause problems, but what does that have to do with version control branch names?

Unlikely, unless his view has changed substantially in the last seven years: https://blog.cleancoder.com/uncle-bob/2017/01/11/TheDarkPath.html

I think his views on how to achieve good quality software are nearly antithetical to the goals of Rust. As expressed in that blog post and in Clean Code, he thinks better discipline, particularly through writing lots and lots of explicit unit tests, is the only path to reliable software. Rust, on the other hand, is very much designed to make the compiler and other tooling bear as much of the burden of correctness as possible.

(To be clear, I realize you’re kidding. But I do think it’s important to know just how at odds the TDD philosophy is from the “safe languages” philosophy.)