←back to thread

Some thoughts on LLMs and software development

(martinfowler.com)
416 points floverfelt | 9 comments | 28 Aug 25 18:52 UTC | HN request time: 0.001s | source | bottom
Show context
sebnukem2 ◴[28 Aug 25 19:28 UTC] No.45056066[source]▶
> hallucinations aren’t a bug of LLMs, they are a feature. Indeed they are the feature. All an LLM does is produce hallucinations, it’s just that we find some of them useful.

Nice.

replies(7): >>45056284 #>>45056352 #>>45057115 #>>45057234 #>>45057503 #>>45057942 #>>45061686 #
1. ninetyninenine ◴[28 Aug 25 19:56 UTC] No.45056352[source]▶
Nah I don't agree with this characterization. The problem is, the majority of those hallucinations are true. What was said would make more sense if the majority of the responses were, in fact, false, but this is not the case.
replies(2): >>45056515 #>>45056567 #
2. ◴[28 Aug 25 20:10 UTC] No.45056515[source]▶
3. xmprt ◴[28 Aug 25 20:16 UTC] No.45056567[source]▶
I think you're both correct but have different definitions of hallucinations. You're judging it as a hallucination based on the veracity of the output. Whereas Fowler is judging it based on the method by which the output is achieved. By that judgement, everything is a hallucination because the user cannot differentiate between when the LLM is telling the truth and isn't.

This is different from human hallucinations where it makes something up because of something wrong with the mind rather than some underlying issue with the brain's architecture.

replies(2): >>45056809 #>>45057305 #
4. ants_everywhere ◴[28 Aug 25 20:42 UTC] No.45056809[source]▶
an LLM hallucination is defined by its truth

> In the field of artificial intelligence (AI), a hallucination or artificial hallucination (also called confabulation,[1] or delusion)[2] is a response generated by AI that contains false or misleading information presented as fact.[3][4]

You say

> This is different from human hallucinations where it makes something up because of something wrong with the mind rather than some underlying issue with the brain's architecture.

For consistency you might as well say everything the human mind does is hallucination. It's the same sort of claim. This claim at least has the virtue of being taken seriously by people like Descartes.

https://en.wikipedia.org/wiki/Hallucination_(artificial_inte...

replies(1): >>45056842 #
5. ninetyninenine ◴[28 Aug 25 20:45 UTC] No.45056842{3}[source]▶
Even the colloquial term outside of AI is characterized by the veracity of the output.
6. BlueTemplar ◴[28 Aug 25 21:34 UTC] No.45057305[source]▶
LLMs don't hallucinate : they bullshit (which is not caring about truth).
replies(1): >>45057712 #
7. ninetyninenine ◴[28 Aug 25 22:22 UTC] No.45057712{3}[source]▶
This isn't a good characterization of it either. I don't think LLMs know the difference. Bullshit implies they are lying.

It's possible LLMs are lying but my guess is that they really just can't tell the difference.

replies(1): >>45060267 #
8. hatefulmoron ◴[29 Aug 25 04:39 UTC] No.45060267{4}[source]▶
They're using the term 'bullshit' as it is understood as a term of art, which doesn't imply lying. It's closer to creating a response without any regard for telling the truth. Bullshitting is often most effective when you happen to be telling the truth, although the bullshitter has no commitment to that.
replies(1): >>45066967 #
9. ninetyninenine ◴[29 Aug 25 17:28 UTC] No.45066967{5}[source]▶
I disagree. IF something is bullshit nobody means that bullshit is possibly true. Bullshit is colloquially always false and always a lie.