@t3rcermillenium@mastodon.social
Post #1470159
2026-01-07 06:12 UTC
@danjones000 @Chip_Unicorn I understand these points.
But do LLMs really need to be deterministic and generate the same code every time?
As long as the output satisfies some defined criteria and passes a set of tests, does it matter what the generated code looks like?
In all likelihood, subsequent debugging, maintenance and new feature addition will also be done by an LLM. Does the code even need to be human readable?
I’m starting to think not.
Replies (2)
-
@liquor_american@universeodon.com 2026-01-07 08:13
@t3rcermillenium @danjones000 @Chip_Unicorn lol
-
@danjones000@microwords.goodevilgenius.org 2026-01-07 14:44
But do LLMs really need to be deterministic and generate the same code every time? If you want to be able to trust them the way you can trust a compiler, than yes, they do. Tests are not the end all be all of whether or not code is good enough. If we can't read the code, we can never be certain that it's doing exactly what we wanted it to do, nothing more and nothing less, consistently with the performance that we expect. LLMs will never give us that. @t3rcermillenium@mastodon.social @Chip_Unicorn@im-in.space