[dist-epoch]

> Models aren't deterministic - every time you would try to re-apply you'd likely get different output

So like when you give the same spec to 2 different programmers.

[rco8786]

Yes, if you had each programmer rewrite the code from scratch each time you updated the spec.

[orbital-decay]

In reality you give the same programmer an update to the existing spec, and they change the code to implement the difference. Which is exactly what the thing in OP is doing, and exactly what should be done. There's simply no reason to regenerate the result.

The entire thing about determinism is a red herring, because 1) it's not determinism but prompt instability, and 2) prompt instability doesn't matter because of the above. Intelligence (both human and machine) is not a formal domain, your inputs lack formal syntax, and that's fine. For some reason this basic concept creates endless confusion everywhere.

[xigoi]

> your inputs lack formal syntax, and that's fine

It’s not fine. I program using formal syntax precisely because I want the computer to do exactly what I tell it to.

[orbital-decay]

Then program, instead of telling someone else (humans, LLMs) to do it.

[xigoi]

I am doing so, but I keep seeing people say that LLMs have completely removed the need for writing code.

[dboreham]

Also like this: https://codeassociates.github.io/conversations-with-claude/c...

[kennywinker]

Except each time you compile your spec you’re re-writing it from scratch with a different programmer.