Nice! This is what I keep telling everyone: LLMs let you build stuff you may not have the time/energy to before. You still need to do the last 10% yourself though. Tying up all the loose ends.

Syntax is a personal choice. Can always be changed. Architectural choices are difficult to manage later on.

The VM seems to be a stack VM. I have my own python replacement project (https://news.ycombinator.com/item?id=48090665) that I am developing privately for now. LLM-assisted ofc. Started with a bytecode VM and then switched over to a register one. The biggest break from regular language systems was the decision to move to an Erlang-style preemptive scheduler.

I completely agree! I started Jaithon before mainstream LLMs existed and for a while Jaithon was free of AI generated code and my personal stance on AI generated code was rather negative. Recently though, my stance has grown far more positive towards AI. While LLMs are undeniably the future it remains crucial that you completely understand the code being generated, and are also in control of the architecture in place. I have tried to adhere to both of these principals while coding :) and it is an unequivocal fact that AI made me atleast 10x more productive. Granted this is a bad measure but still a measure of such: in the last 2 days I have made the same number of commits as I have to Jaithon in the last 3 years.

Also, I was curious why you swapped over to a register based VM, could you give more clarity on that and the benifits/negatives? currently im using some sort of bytecode vm, though its not like im married to the idea of a bytecode vm.

Also (dont mean this as any sort of advertisement or anything like that) would you mind starring the repo? trying to hit 15 stars :D dont feel forced or anything like that.