Finally I am not even confident in the standard definition of knowledge anymore. For all I know you just know how to answer questions.
The definition of knowledge is a lot like the one of conscience: there are 9001 of them, and they all suck, but you stick to one or another as it’s convenient.
In this case I’m using “knowledge = justified and true belief” because you can actually use it past human beings (e.g. for an elephant passing the mirror test)
Also “knowing self” is just another way of saying meta-cognition something it can do to a limit extent.
Meta-cognition and conscience are either the same thing or strongly tied to each other. But I digress.
When you say that it can do it to a limited extent, you’re probably referring to output like “as a large language model, I can’t answer that”? Even if that was a belief, and not something explicitly added into the model (in case of failure, it uses that output), it is not a justified belief.
My whole comment shows why it is not justified belief. It doesn’t have access to reason, nor to experience.
Seems a valid answer. It doesn’t “know” that any given Jane Etta Pitt son is. Just because X -> Y doesn’t mean given Y you know X. There could be an alternative path to get Y.
If it was able to reason, it should be able to know the second proposition based on the data used to answer the first one. It doesn’t.
Your entire argument boils down to because it wasn’t able to do a calculation it can do none. It wasn’t able/willing to do X given Y so therefore it isn’t capable of any time of inference.
Your entire argument boils down to because it wasn’t able to do a calculation it can do none.
Except that it isn’t just “a calculation”. LLMs show consistent lack of ability to handle an essential logic property called “equivalence”, and this example shows it.
And yes, LLMs, plural. I’ve provided ChatGPT 3.5 output, but feel free to test this with GPT4, Gemini, LLaMa, Claude etc.
Just be sure to not be testing instead if the LLM in question has a “context” window, like some muppet ITT was doing.
It wasn’t able/willing to do X given Y so therefore it isn’t capable of any time of inference.
Emphasis mine. That word shows that you believe that they have a “will”.
Now I get it. I understand it might deeply hurt the feelings of people like you, since it’s some unfaithful one (me) contradicting your oh-so-precious faith on LLMs. “Yes! They’re conscious! They’re sentient! OH HOLY AGI, THOU ART COMING! Let’s burn an effigy!” [insert ridiculous chanting]
Sadly I don’t give a flying fuck, and examples like this - showing that LLMs don’t reason - are a dime a dozen. I even posted a second one in this thread, go dig it. Or alternatively go join your religious sect in Reddit LARPs as h4x0rz.
“Yes! They’re conscious! They’re sentient! OH HOLY AGI, THOU ART COMING! Let’s burn an effigy!” [insert ridiculous chanting]
Sadly I don’t give a flying fuck…
“Let’s focus on practical philosophical matters…”
Such as your sarcasm towards people who disagree with you and your “not giving a fuck” about different points of view?
Maybe you shouldn’t be bloviating on the proper philosophical method to converse about such topics if this is going to be your reaction to people who disagree with your arguments.
I’ll quote out of order, OK?
The definition of knowledge is a lot like the one of conscience: there are 9001 of them, and they all suck, but you stick to one or another as it’s convenient.
In this case I’m using “knowledge = justified and true belief” because you can actually use it past human beings (e.g. for an elephant passing the mirror test)
Meta-cognition and conscience are either the same thing or strongly tied to each other. But I digress.
When you say that it can do it to a limited extent, you’re probably referring to output like “as a large language model, I can’t answer that”? Even if that was a belief, and not something explicitly added into the model (in case of failure, it uses that output), it is not a justified belief.
My whole comment shows why it is not justified belief. It doesn’t have access to reason, nor to experience.
If it was able to reason, it should be able to know the second proposition based on the data used to answer the first one. It doesn’t.
Your entire argument boils down to because it wasn’t able to do a calculation it can do none. It wasn’t able/willing to do X given Y so therefore it isn’t capable of any time of inference.
Except that it isn’t just “a calculation”. LLMs show consistent lack of ability to handle an essential logic property called “equivalence”, and this example shows it.
And yes, LLMs, plural. I’ve provided ChatGPT 3.5 output, but feel free to test this with GPT4, Gemini, LLaMa, Claude etc.
Just be sure to not be testing instead if the LLM in question has a “context” window, like some muppet ITT was doing.
Emphasis mine. That word shows that you believe that they have a “will”.
Now I get it. I understand it might deeply hurt the feelings of people like you, since it’s some unfaithful one (me) contradicting your oh-so-precious faith on LLMs. “Yes! They’re conscious! They’re sentient! OH HOLY AGI, THOU ART COMING! Let’s burn an effigy!”
[insert ridiculous chanting]Sadly I don’t give a flying fuck, and examples like this - showing that LLMs don’t reason - are a dime a dozen. I even posted a second one in this thread, go dig it. Or alternatively go join your religious sect in Reddit LARPs as h4x0rz.
/me snaps the pencilSomeone says: YOU MURDERER!“Let’s focus on practical philosophical matters…”
Such as your sarcasm towards people who disagree with you and your “not giving a fuck” about different points of view?
Maybe you shouldn’t be bloviating on the proper philosophical method to converse about such topics if this is going to be your reaction to people who disagree with your arguments.