Post

Any experts on #LLM who can shed some light on this? As we now can use ChatGPT and such to generate code for an entire application/system, why do we have to go through a high level language and not just generate machine code directly?

I think it can[1] but we don’t do it because: 1) we don’t trust the LLM enough. We want to review the code. 2) high level languages give you a higher density of expression per token. i.e. it takes less tokens so you get faster answers [1] chatgpt.com/share/674db3...

Yeah I get what you’re saying. But I’d caution against dismissing people because they don’t speak for _everyone_. I am an expert 😂 and while I trust LLMs for many things, me and most of my friends very much would not trust an LLM machine code output.

That's fair. I'm mostly interested from a technical point of view. Do you think the LLMs will get better at machine code eventually so that it is mostly about getting them trained on enough data?