Hacker News Reader

Comment by devmor | Hacker News Reader

No, your original understanding was the more correct one. There is absolutely zero logic to be found inside an LLM, other than coincidentally.

What you are seeing is a semi-randomized prediction engine. It does not "know" things, it only shows you an approximation of what a completion of its system prompt and your prompt combined would look like, when extrapolated from its training corpus.

What you've mistaken for a "logical model" is simply a large amount of repeated information. To show the difference between this and logic, you need only look at something like the "seahorse emoji" case.

View on HN

No, their revised understanding is more accurate. The model has internal representations of concepts; the seahorse emoji fails because it uses those representations and stumbles: https://vgel.me/posts/seahorse/

Word2vec can/could also do the seahorse thing. It at least seems like there's more to what humans consider a concept than a direction in a vector space model (but maybe not).

https://www.analyticsvidhya.com/blog/2021/07/word2vec-for-wo...

No, this is not a demonstration of logic or knowledge. It is a demonstration of a relational database.

A markov chain presents the same representation in a lower vector space.

If anything, the seahorse emoji case is exactly the type of thing you wouldn't expect to happen if LLMs just repeated information from their training corpus. It starts producing a weird dialogue that's completely unlike its training corpus, while trying to produce an emoji it's never seen during training. Why would it try to write an emoji that's not in its training data? This is totally different than its normal response when asked to produce a non-existent emoji. Normally, it just tells you the emoji doesn't exist.

So what is it repeating?

It's not enough to just point to an instance of LLMs producing weird or dumb output. You need to show how it fits with your theory that they "just repeating information". This is like pointing out one of the millions of times a person has said something weird, dumb, or nonsensical and claiming it proves humans can't think and can only repeat information.

> It starts producing a weird dialogue that's completely unlike its training corpus

But it's not doing that. It's just replacing a relation in vector space with one that we would think is distant.

Of course you would view an LLM's behavior as mystifying and indicative of something deeper when you do not know what it is doing. You should seek to understand something before assigning mysterious capabilities to it.

You're not addressing the objection. What is it about your model of how you think LLMs work (that it's just "repeated information") that predicts they'd go haywire when asked about a seahorse emoji (and only the seahorse emoji)? Why does your model explain this better than the standard academic view of deep neural nets?

You just pointed out an example of LLMs screwing up and then skipped right to "therefore they're just repeating information" without showing this is what your explanation predicts.

If you want to have a conversation with me, please stop creating fake quotes and assigning them to me, and please stop lying.

"repeated information" was copied verbatim from your comment. Your full sentence was:

> What you've mistaken for a "logical model" is simply a large amount of repeated information.

If you copy two words from me and put them in a difference sentence that means something else, that's a lie. If you want to argue with a strawman, that's something you can go rely on an LLM for instead of me.

I haven't lied. You're making accusations in bad faith. This was a faithful representation of your position as best as I can tell from your comment.

If you'd like to explain why "What you've mistaken for a 'logical model' is simply a large amount of repeated information." actually means something else, or why you think I've misinterpreted it, be my guest.

> There is absolutely zero logic to be found inside an LLM

Surely trained neural networks could never develop circuits that implement actual logic via computational graphs...

https://transformer-circuits.pub/2025/attribution-graphs/met...

You're both using two different definitions of the word "logic". Both are correct usages, but have different contexts.

I often wonder whether neuroscience on LLMs is harder or humans?

Brute force engineering solutions to appear like the computer is thinking. When we have no idea how we think ourselves. This will never generate true intelligence. It executes code, then it stops, it is a tool, nothing more.

Reply on news.ycombinator.com