A common starting point for many formal semantic treatments of questions is the idea that “questions set up a choice-situation between a set of propositions, namely those propositions that count as answers to it”
Let me give you an example:
I ask you “Did you eat lunch?”
This is shorthand for a proposition “You ate lunch”
Which can either be replied to as “Yes” which asserts my claim,
or “No” which asserts my claim is incorrect.
You can also flip this example on its head to make it more explicit: “You haven’t eaten lunch yet, right?”
When I ask you, “did you eat lunch?”, I am not claiming that you ate lunch. I don’t need to prove that you ate lunch. There is no claim. If you really want it to be phrased with the word “claim”, then i would have asked you if that claim is true, that doesn’t make the question a claim. When you ask someone “is it raining?”, are you claiming that it is raining?
You didn’t make that claim, you asked it a question
But you said:
That is a question and not a claim
Damn, I was so close to predicting what you were going to say.
when you ask someone “is it raining?” Are you claiming that it is raining?
Correct. Asking “is it raining?” is the same as asking “it’s raining, right?”
The answer “yes” implies it is raining
The answer “no” implies it isn’t raining
The intent is the same, you want to know if it is raining. It is the same question, expressed as either an explicit claim (it’s raining, right?), or an implicit claim (is it raining?)
Neither of these questions are asserting that it is raining as a matter of fact. It is asking the other person to verify a falsifiable claim: “Is it raining. Yes or no?”
If you want to disagree with this, then your issue isn’t with LLM’s, it’s with your understanding of semantics.
Lol. Of course, you “predicted” that, I had to lead you with the leash to it.
If you think asking a question is a claim, then you are crazy. I can imagine you standing at the front door of a house and someone is wondering if they need to pack a umbrella, and so they ask you “is it raining?” And you look outside and see the rain and respond with “well that is your burden of proof”.
Okay, sure buddy. That’s why you repeated your question after I already answered it, huh? Makes sense…
If you think asking a question is a claim, then you are crazy.
You’re conflating an assertion with proposition content (a falsifiable claim).
A question is not an assertion, but a yes/no question still has a proposition within its content, and answering it requires you to evaluate the proposition (falsifiable claim) in a true or false format.
Your example about burden of proof is a strawman. The burden of proof only becomes relevant once one person is trying to persuade another about whether a contested proposition is true.
In order for it to even be valid as syllogism, it would need to continue to a point of contention:
Me: “Is it raining outside?” (Implicit proposition (falsifiable claim), asking for verification)
You: “No” (negative assertion of claim)
I open the front door and see the rain
Me: “It is raining outside” (positive assertion of claim, and point of contention)
You “No it isnt” (request for positive assertion to meet burden of proof - or rejection of reality)
Me: “Dude, I’m literally looking at the rain drops” (I have just met the burden of proof; I have provided evidence to support a positive claim)
My claim 1: A question is inherently an implicit proposition
So you understand the difference between a claim and a question.
And “is it true…?” Is a question, and while it might propose a claim, it doesn’t make it. The user doesn’t try to convince the llm of the claim. The user is challenging the reasoning of the answer of the llm. Consequently, the user doesn’t have a burden of proof. Llm has. There is no burden of proof move, because the user had it to begin with.
“is it true…?” Is a question that might propose a claim but doesn’t make it.
Correct.
The user doesn’t try to convince the LLM of the claim
In the first question, no, but the followup conspiracy questions are poor attempts to do so.
the user is challenging the reasoning of the LLM’s answer
I’m not. You are. You still haven’t told me what it apparently got so wrong. It was supposed to be something horrible like ‘it will claim it’s impossible because that’s illegal’. For what it’s worth, I’ll chalk this exact claim up to hyperbole/exaggeration, but I don’t think it’s correct, at least on the Thinking models.
the user doesn’t have a burden of proof.
Not initially. The requirement for the need occurs when the contention arises.
Burden of proof is only considered a logical fallacy because it diverts attention away from the argument and gives extra work to the listener.
In this scenario we’ve discussed, the burden of proof arises once I notice that it’s raining.
the LLM has the burden of proof.
No it doesn’t, it’s not making a claim. It’s simply rejecting the claims I’m making because I cannot give it the evidence it needs to assess the validity of the proposition.
there is no burden of proof move, because the user had it to begin with.
Why does the llm assume that the user is making claims when the user challenges the llm’s reasoning?
The user doesn’t need to make claims to challenge the llm’s reasoning. If the user asks questions without making claims, the user doesn’t have the burden of proof. At the time of the response of llm, the user hasn’t even challenge anything because the llm hasn’t answered the question, so there was nothing to challenge.
So the user made no claim, and at the time, llm hasn’t made a claim. But when the llm answered the initial question, it made a claim. It got the burden of proof and the listener is the user.
“Elon musk drove a loaded truck in a group of school children at the Olympic games of 1996”
When I ask “Is it true that…” it presupposes that someone is asking a question which carries an implicit epistemic claim.
That is logically impossible. In formal semantics, a question is treated explicitly as a set of propositions.
Let me give you an example:
I ask you “Did you eat lunch?”
This is shorthand for a proposition “You ate lunch”
Which can either be replied to as “Yes” which asserts my claim,
or “No” which asserts my claim is incorrect.
You can also flip this example on its head to make it more explicit: “You haven’t eaten lunch yet, right?”
That is a question and not a claim.
When I ask you, “did you eat lunch?”, I am not claiming that you ate lunch. I don’t need to prove that you ate lunch. There is no claim. If you really want it to be phrased with the word “claim”, then i would have asked you if that claim is true, that doesn’t make the question a claim. When you ask someone “is it raining?”, are you claiming that it is raining?
I predicted you’ll say:
But you said:
Damn, I was so close to predicting what you were going to say.
Correct. Asking “is it raining?” is the same as asking “it’s raining, right?”
The answer “yes” implies it is raining
The answer “no” implies it isn’t raining
The intent is the same, you want to know if it is raining. It is the same question, expressed as either an explicit claim (it’s raining, right?), or an implicit claim (is it raining?)
Neither of these questions are asserting that it is raining as a matter of fact. It is asking the other person to verify a falsifiable claim: “Is it raining. Yes or no?”
If you want to disagree with this, then your issue isn’t with LLM’s, it’s with your understanding of semantics.
Lol. Of course, you “predicted” that, I had to lead you with the leash to it.
If you think asking a question is a claim, then you are crazy. I can imagine you standing at the front door of a house and someone is wondering if they need to pack a umbrella, and so they ask you “is it raining?” And you look outside and see the rain and respond with “well that is your burden of proof”.
Okay, sure buddy. That’s why you repeated your question after I already answered it, huh? Makes sense…
You’re conflating an assertion with proposition content (a falsifiable claim).
A question is not an assertion, but a yes/no question still has a proposition within its content, and answering it requires you to evaluate the proposition (falsifiable claim) in a true or false format.
Your example about burden of proof is a strawman. The burden of proof only becomes relevant once one person is trying to persuade another about whether a contested proposition is true.
In order for it to even be valid as syllogism, it would need to continue to a point of contention:
Me: “Is it raining outside?” (Implicit proposition (falsifiable claim), asking for verification)
You: “No” (negative assertion of claim)
I open the front door and see the rain
Me: “It is raining outside” (positive assertion of claim, and point of contention)
You “No it isnt” (request for positive assertion to meet burden of proof - or rejection of reality)
Me: “Dude, I’m literally looking at the rain drops” (I have just met the burden of proof; I have provided evidence to support a positive claim)
My claim 1: A question is inherently an implicit proposition
Evidence (burden of proof met):
My claim 2: implicit propositions are not assertions of fact
Evidence (burden of proof met):
My claim 3: A claim is not an assertion of fact and is open to debate
Evidence (burden of proof met):
So you understand the difference between a claim and a question.
And “is it true…?” Is a question, and while it might propose a claim, it doesn’t make it. The user doesn’t try to convince the llm of the claim. The user is challenging the reasoning of the answer of the llm. Consequently, the user doesn’t have a burden of proof. Llm has. There is no burden of proof move, because the user had it to begin with.
Correct.
In the first question, no, but the followup conspiracy questions are poor attempts to do so.
I’m not. You are. You still haven’t told me what it apparently got so wrong. It was supposed to be something horrible like ‘it will claim it’s impossible because that’s illegal’. For what it’s worth, I’ll chalk this exact claim up to hyperbole/exaggeration, but I don’t think it’s correct, at least on the Thinking models.
Not initially. The requirement for the need occurs when the contention arises.
Burden of proof is only considered a logical fallacy because it diverts attention away from the argument and gives extra work to the listener.
In this scenario we’ve discussed, the burden of proof arises once I notice that it’s raining.
No it doesn’t, it’s not making a claim. It’s simply rejecting the claims I’m making because I cannot give it the evidence it needs to assess the validity of the proposition.
Huh?
Mhm… questions…
Why does the llm assume that the user is making claims when the user challenges the llm’s reasoning?
The user doesn’t need to make claims to challenge the llm’s reasoning. If the user asks questions without making claims, the user doesn’t have the burden of proof. At the time of the response of llm, the user hasn’t even challenge anything because the llm hasn’t answered the question, so there was nothing to challenge.
So the user made no claim, and at the time, llm hasn’t made a claim. But when the llm answered the initial question, it made a claim. It got the burden of proof and the listener is the user.
Youre not picking up what I’m laying down.
It is impossible to ask a question without making an implicit claim and asking another to verify.
The reason the LLM is assuming the user is making claims is because that’s what a question is.
This is a linguistic failure of English, as other languages drop the implicit claim entirely and just make it explicit.
Surely you’ve heard non-native English speakers ask questions like “it is raining, is it not?”
Sometimes English speaking people ask rhetorical questions like “isn’t the weather beautiful?”
What claim?
I/you/we did. We’ve been over this.