Hacker News Reader

Comment by avianlyric | Hacker News Reader

Isn’t the entire paper is trying to point out that the second you ask the question “Do LLM have <anthropomorphic property X>”, you have to assume that they do, even before you make any assessment?

Just because the person asking the question isn’t aware of they’re implicitly making that assumption, doesn’t change the fact that a logical assumption has been made. It just makes the questioner ignorant of the assumptions they’re making.

Personally don’t totally understand the argument being made in the paper. But I can understand the idea that I can ask a question, without properly understanding the assumptions I’m making when asking the questions. Indeed I can also understand that I might not even notice the assumptions I’ve made with my question, and why that would make my entire exploration and conclusion invalid, _after_ doing the investigation. Logical fallacies can be really difficult to spot and understand.

View on HN

> the second you ask the question “Do <things> have <property>”, you have to assume that they do

being able to imagine something doesn't mean believing in it?

I completely fail to understand the argument

I feel like there's some mistake in confusing 2 meanings of "assume" - one where it's close to 100% probability and one where it's close to 0% probability.

> being able to imagine something doesn't mean believing in it?

In general, no, but some assumptions come with such heavy implicit baggage that you arguably do.

An example can be, the question, "does anything matter?".

By asking that question, you have allowed for the possibility that some things matter. But if you allow for that possibility, you might as well believe it - because if it's wrong, by definition it doesn't matter that you're wrong.

This argument doesn't prove that anything matters. But it proves that you already assumed that some things matter.

> prove that anything matters

The proveability itself seems based upon assumption.

This invites the question of whether assumptions have assumed the role of anti-matter.

> the second you ask the question “Do LLM have <anthropomorphic property X>”, you have to assume that they do … Just because the person asking the question isn’t aware of they’re implicitly making that assumption, doesn’t change the fact that a logical assumption has been made. It just makes the questioner ignorant of the assumptions they’re making.

1. Do LLMs have loyalty?

2. Do LLMs have sorrow?

3. Do LLMs have moods?

4. Do LLMs have destinies?

5. Do LLMs have spirits?

6. Do LLMs have holidays?

7. Do LLMs have a sense of boredom?

I say I don't believe LLMs have those properties, but you believe that since I asked those questions that I actually must assume LLMs must have them?

Also, is this specific to LLMs, or if someone asked questions like "Does a blade of grass (etc) have <anthropomorphic property X>?", you have to assume they do?

Reply on news.ycombinator.com