[sheepscreek]

I think, we’re not far from the day when LLMs will be spitting out highly optimized ilasm/byte-code (dotnet intermediate language representation). So your programming language will well and truly be a bunch of prompts. That’s it.

[suprjami]

I think that's unlikely to get widespread traction.

Source code is not for computers, it is a way for human developers to communicate with each other.

Compilers/interpreters are a consumer of that communication.

Without easy communication of ideas, software does not work. That's why very few people write in raw assembly (hardware or bytecode) and why so many people write in programming languages.

LLMs will not remove the human interchange of ideas. At least not the current generation of generative LLMs.

[ofrzeta]

How to you review the resulting bytecode? Or will you just go on running it blindly on some computer on the Internet?

[adzm]

What would be the benefit to this versus generating highly optimized c# for example?

[lihaciudaniel]

The benefit to this is that we talk in tokens, no longer bytes. The Microsoft era where you had to work in bytes is over, now we work with tokens e.g: I build a snake game with 500 tokens, welcome to the future!