[chubot]

Without being glib, I honestly wonder if Fabrice Bellard has started using any LLM coding tools. If he could be even more productive, that would be scary!

I doubt he is ideologically opposed to them, given his work on LLM compression [1]

He codes mostly in C, which I'm sure is mostly "memorized". i.e. if you have been programming in C for a few decades, you almost certainly have a deep bench of your own code that you routinely go back to / copy and modify

In most cases, I don't see an LLM helping there. It could be "out of distribution", similar to what Karpathy said about writing his end-to-end pedagogical LLM chatbot

---

Now that I think of it, Bellard would probably train his own LLM on his own code! The rest of the world's code might not help that much :-)

He has all the knowledge to do that ... I could see that becoming a paid closed-source project, like some of his other ones [2]

[1] e.g. https://bellard.org/ts_zip/

[2] https://bellard.org/lte/

[latenightcoding]

What I wonder is: are current LLMs even good for the type of work he does: novel, low-level, extremely performant

[vitaminCPP]

As a professional C programmer, the answer seems to be no; they are not good enough.

[vbezhenar]

I'm writing C for microcontrollers and ChatGPT is very good at it. I don't let it write any code (because that's the fun part, why would I), but I discuss with it a lot, asking questions, asking to review my code and he does good. I also love to use it to explain assembly.

[mhh__]

This is a funny one because on the one hand the answer is obviously no, it's very fiddly stuff that requires a lot of umming and ahhing, but then weirdly they can be absurdly good in these kinds of highly technical domains precisely because they are often simple enough to pose to the LLM that any help it can give is actually applicable immediately whereas in a comparatively boring/trivial enterprise application there is a vast amount of external context to grapple with.

[wolttam]

If Fabrice explained what he wanted, I expect the LLM would respond in kind.

[rjzzleep]

From my experience, it's just good enough to give you a code overview of a codebase you don't know and give you enough implementation suggests to work from there.

[koakuma-chan]

No

[slekker]

I doubt it, although LLMs seem to do well on low-level (ASM level instructions).

[raverbashing]

I think it's the opposite: llms ask Fabrice Bellard instead

[jacquesm]

Congrats, the Chuck Norris meme has finally made its way onto HN.

[echelon]

They're trained on his code for sure. Every time I ask about ffmpeg internals, I know it's Fabrice's training data.

[MrDrMcCoy]

He has in fact written one: https://bellard.org/ts_server/

[chubot]

Yeah I've seen that, but it looks like the inference-side only?

Maybe that is a hint that he does use off-the-shelf models as a coding aid?

There may be no need to train your own, on your own code, but it's fun to think about

[lomase]

Why every single post in HN has to come down to talk about AI sloop...

[rdtsc]

> Without being glib, I honestly wonder if Fabrice Bellard has started using any LLM coding tools

I doubt it. I follow him and look at the code he writes and it's well thought out and organized. It's the exact opposite of AI slop I see everywhere.

> He codes mostly in C, which I'm sure is mostly "memorized". i.e. if you have been programming in C for a few decades,

C I think he memorized a long time ago. It's more like he keeps the whole structure and setup of the program (the context) in his head and is able to "see it" all and operate on it. He is so good that people are insinuating he is actually "multiple people" or he uses an LLM and so on. I imagine he is quite amused reading those comments.

[MangoToupe]

Still, humans can only type so quickly. It's not hard to imagine how even a flawless coder could benefit from an llm.

[furbdiba]

Keep in mind even if someone writes their own code LLM is great to accelerate: tests, makefiles, docs, etc.

Or it can review for any subtle bugs too. :)

[agumonkey]

Some talented people (mitsuhiko, Evan you) seem to leverage LLM their own way. Probably as legwork mostly.

[globalnode]

Is Fabrice like the Chuck Norris of programming?

[Renaud]

Hopefully without the politics…

[throwaway2037]

In 2025, there is no shame in using an LLM. For example, he might use it to get help debugging, or ask if a block of code can be written more clearly or efficiently.

[gyomu]

> I honestly wonder if Fabrice Bellard has started using any LLM coding tools. If he could be even more productive, that would be scary!

That’s kind of a weird speculation to make about creative people and their processes.

If Caravaggio had had a computer with Photoshop, if Eintein had had a computer with Matlab, would they have been more productive? Is it a question that even makes sense?

[Kiro]

> Is it a question that even makes sense?

Absolutely. It's a very intriguing thought invoking the opposite of the point you're trying to make.

[nextaccountic]

Maybe today Bellard uses LLMs though

[lomase]

Matlab has been proven to be a indispensable tool in many fields.

AI is the same, for example creating slop or virtual girlfriends.