[krupan]

I still can't understand why people believe that this is the future. Especially for green field work like new compilers. LLMs do not invent new things. They cannot produce anything smarter/better than what they have been trained on. The big advantage they provide is producing (regurgitating) code faster than humans and better than less experienced/knowledgeable humans.

[umvi]

Ultimately code is an iterative refining process, like sculpting granite or spinning pottery. You start rough and iteratively shape and polish it. LLMs just rapidly speedup the iterative process. The next generation will be using LLMs to quickly setup the rough shape of new software and then iteratively refine them.

The "smarter/better" attributes you are worried about LLMs not having happen between iterative steps, when the human is inspecting the current state of the software and compares it to the desired state of the software (in their mind's eye). The human then course corrects for the next iteration.

This would be like if Michelangelo carved the David using a robotic 6-axis chisel. It takes him 1 month instead of 3 years because he can convey his initial vision to the robot and then iteratively refine the granite until it matches his vision.

You can try to claim LLMs don't invent new things, but humans using LLMs absolutely invent new things (source: myself).

[krupan]

That was a lot of words to agree with me that LLMs don't invent new things

[umvi]

OP said "The next generation of developers will, for better or worse, grow up using AI assistance to write their code, but none of them will ever become a Zig contributor."

You rebutted with (paraphrasing) "no, you can't build compilers with LLMs because LLMs don't invent new things"

I used a lot of words to demonstrate that you can invent new things with LLMs, including compilers, as long as it's a human + LLM iterative loop and not an unsupervised LLM running in a vacuum.

[krupan]

To me it sounds like you did all the actual hard work of the inventing. If an LLM brainstormed some ideas and you validated which ones worked and implemented the idea and fully grokked the code then the zig developers probably wouldn't ever know that an LLM was involved and you'd be fine to contribute.

[chickensong]

LLMs are the future because you have an amazing amount of information available with low friction, plus the ability to reason (sort of) about things. In some cases they might regurgitate, but they're also pretty good at synthesizing and comparing. None of this is perfect, but nothing else is either.

LLMs are a powerful tool like we've never had before. You don't expect a chainsaw to cut down a tree by itself and carve the wood into a statue or a new compiler. LLMs aren't mind-reading autonomous creators, they're more like a mech suit that can increase your capabilities. They have flaws, but until something better comes along, it sure seems like they're the future.