Post #1470157

2026-01-06 23:51 UTC

@Chip_Unicorn Ok, so old enough to have transitioned from asm to C in the 80’s. The first compilers were shit; I spent a load to time looking at the generated asm for the C code we wrote. It was shit. But that passed. Now we “trust” compilers. Now I spend a lot of time looking at the code generated by Claude, and it works. But it’s shit code. But this too, will pass. Soon, I won’t look at the code generated by Claude. At least, that’s the ideal. Let’s see how that works out.

Replies (1)

@danjones000@microwords.goodevilgenius.org 2026-01-07 05:11

This is a pretty bad take. We trust compilers not just because they work well, but because we can actually trust them to always do what their told to do. Compilers are deterministic. Given the same code, a compiler will produce the same machine code on the same machine 100% of the time, without fail. LLMs are not designed to do that, and never will be. If they were, they'd just be compilers, but that has never been a design goal of LLMs. There will never be a point in time where you can just trust the code output by an LLM the way you can a compiler, because they are non-deterministic. @t3rcermillenium@mastodon.social @Chip_Unicorn@im-in.space

Open ##1470158