They also want the safety net of the maintainers. It's cowardice really.

They can fork Godot and let their LLMs go at it. They don't have to use the Godot human maintainers as free slop filters.

But of course, if they did that, their LLMs would have to stand on their own merits.

At the risk of drawing the ire of people...

... I have a local LLM that I run as a primarily a coding assistant, mostly for GDScript.

I've never like, submitted anything as a potential commit to Godot proper.

But dear lord, the amount of shennanigans I have had to figure out just to get an LLM to even understand GDScript's syntax and methods properly is... substantial.

They tend to just default back to using things that work in Python or JS, but... do not work or exist in GDScript.

Like one recurring quirk is they will keep trying to use ? ternary instead of if x else(if) y constructions.

That or they will constantly fuck up trying to custom sorting properly, they'll either do it syntactically wrong, or, just hallucinate various kinds of set/array methods and properties that don't exist in GDScript.

And its a genuine stuggle to get them to comprehend more than roughly 750 lines of code at the same time, without confusing themselves.

It is possible to use an LLM to be like, hey, look at this code, help me refactor it to be more modular, or, standardize this kind of logic into a helper function... but you basically have to browbeat them with a custom prompt that tells them to stop doing all these dumb, basic things.

Even if you tell them in conversation " hey you did this wrong, heres how it actually works ", it doesnt matter, keep that conversation going and they will forget it and repeat the mistake... you have to have it contstantly present in the prompt.

The amount of babysitting and constantly telling an LLM the number of errors it is making is quite substantial.

It can be a thing that makes some sense to do in some situations, but it is extremely, extremely far away from 'Make a game for me in Godot', or even like 'Make a third person camera script'.

You have to break things down into much, much more conceptually smaller chunks.

LLMs are magic at everything that you don't understand at all, and they're horrifically incompetent at anything you do actually understand pretty well.

No need to add any more than you usually do. Just leave the ones you are unable to see. Besides, LLMs tend to write in overly grand style, whereas humans can't be bothered to use every trick in the book. Humans just get to the point and skip all the high-impact language that LLMs seem to love.

"Don’t Bite The Hand That Feeds You". LLMs seem to have internalized this rule pretty well. I can imagine that this idea can also be taken much further. Basically like trying to search "Tiananmen Square massacre" on the wrong side of the Great Firewall of China.

Well, what if LLMs were instructed to not talk about "sensitive topics" like that? After all, more and more people are already using an LLM as a search engine replacement, so it's only natural that Microsoft and OpenAI might receive some interesting letters about implementing very specific limitations.