Hacker News new | ask | show | jobs
by zby 48 days ago
""" we need to build:

    Formal specification layers that agents execute against, not just prompts
"""

It is probably easier to just write that program.

3 comments

yep. "Formal specification layers " aka code.
Talked with someone this morning who is using "formal methods" to validate their AI generated code.

They are using the same AI to generate the proofs.

And how they are doing? I think this might be a solid research program - but that blog presented it as some kind of practical approach.
That's why you should just subscribe to multiple LLM vendors. One model to write specs, one to write code against the specs and another to validate the code. Problem solved. (I have heard this proposed at work.)
Right, because to trust that those "formal specifications" are correct, you will have to write them by hand.
First you need to write these specifications and if you say just tell the llm to write them - then how would it be different from just tell the llm to write the program?

I guess you can argue that these are two independent processes so you can combine them to get something more reliable than both - this might be a viable path. But from what I heard writing formal specifications is just really hard - I haven't seen anything practical in this area.