←back to thread

1257 points adrianh | 1 comments | | HN request time: 0.335s | source
Show context
JimDabell ◴[] No.44491678[source]
I wrote this the other day:

> Hallucinations can sometimes serve the same role as TDD. If an LLM hallucinates a method that doesn’t exist, sometimes that’s because it makes sense to have a method like that and you should implement it.

https://www.threads.com/@jimdabell/post/DLek0rbSmEM

I guess it’s true for product features as well.

replies(2): >>44491913 #>>44496172 #
AdieuToLogic ◴[] No.44496172[source]
> I wrote this the other day:

>> Hallucinations can sometimes serve the same role as TDD. If an LLM hallucinates a method that doesn’t exist, sometimes that’s because it makes sense to have a method like that and you should implement it.

A detailed counterargument to this position can be found here[0]. In short, what is colloquially described as "LLM hallucinations" do not serve any plausible role in software design other than to introduce an opportunity for software engineers to stop and think about the problem being solved.

See also Clark's third law[1].

0 - https://addxorrol.blogspot.com/2025/07/a-non-anthropomorphiz...

1 - https://en.wikipedia.org/wiki/Clarke%27s_three_laws

replies(1): >>44496650 #
1. JimDabell ◴[] No.44496650[source]
Did you mean to post a different link? The article you linked isn’t a detailed counterargument to my position and your summary of it does not match its contents either.

I also don’t see the relevance of Clarke’s third law.