Hacker News Reader

I never thought of that. Humans avoid machine code for many reasons. If LLM's don't need to produce human-readable output, then why not?

View on HN

It would be architecture dependent

Well they could output plan.md files that are architecture independent first. Then we can commit those, and only generate the final machine code on demand.

That's a very good way to ensure your software is not reproducible.

People don't trust other people making little changes to existing software, who will ever be ok with rebuilding it from scratch?

We could call the final phase a coLLMpiler for good measure.

Reply on news.ycombinator.com