A Multi-Level View of LLM Intentionality
disagreeableme.blogspot.com
A Multi-Level View of LLM Intentionality
1–10 of 75 posts
Re: A Multi-Level View of LLM Intentionality
#2>Unless you think that there is some fundamental reason why LLMs will never be able to play chess competently, and I doubt there is, then it seems that we could with the right prompts implement some sort of chess AI using an LLM.
You can play a good game of chess (or poker for that matter) with GPT.
https://twitter.com/kenshinsamurai9/status/16625105325852917...
https://arxiv.org/abs/2308.12466
There's also some work going on in the eleuther ai discord training LLMs specifically for chess to see how they shape up. They're using the pythia models. so far:
Pythia 70M, est ELO 1050
Pythia 160M, est ELO 1370
Re: A Multi-Level View of LLM Intentionality
#3The authors of the text the model was trained on certainly had intentions. Many of those are going to be preserved in the output.
Re: A Multi-Level View of LLM Intentionality
#4>Unless you think that there is some fundamental reason why LLMs will never be able to play chess competently, and I doubt there is, then it seems that we could with the right prompts implement some sort of chess AI using an LLM. You can play a good game of chess (or poker for that matter) with GPT. https://twitter.com/kenshinsamurai9/status/16625105325852917... https://arxiv.org/abs/2308.12466 There's also some work…
I've found they fall apart after a couple of moves and lose track of the game.
Edit: This might not be the case anymore it seems, my below point doesn't actually contradict you, seems it matters a lot how you tell the model your moves. Also saying things like "move my rightmost pawn" completely confuses them.
Re: A Multi-Level View of LLM Intentionality
#5>Unless you think that there is some fundamental reason why LLMs will never be able to play chess competently, and I doubt there is, then it seems that we could with the right prompts implement some sort of chess AI using an LLM. You can play a good game of chess (or poker for that matter) with GPT. https://twitter.com/kenshinsamurai9/status/16625105325852917... https://arxiv.org/abs/2308.12466 There's also some work…
I've found they fall apart after a couple of moves and lose track of the game. Edit: This might not be the case anymore it seems, my below point doesn't actually contradict you, seems it matters a lot how you tell the model your moves. Also saying things like "move my rightmost pawn" completely confuses them.
Not had it lose track with the format in the first link (GPT-4, not really tried 3.5)
Re: A Multi-Level View of LLM Intentionality
#6Earlier quoted context omitted.
I've found they fall apart after a couple of moves and lose track of the game. Edit: This might not be the case anymore it seems, my below point doesn't actually contradict you, seems it matters a lot how you tell the model your moves. Also saying things like "move my rightmost pawn" completely confuses them.
Not had it lose track with the format in the first link (GPT-4, not really tried 3.5)
Yeah i was wrong. I think it has gotten better since i tried this.
Re: A Multi-Level View of LLM Intentionality
#7The authors of the text the model was trained on certainly had intentions. Many of those are going to be preserved in the output.
Can we say ChatGPT or its future versions would be like an instantiation of the Boltzmann Brain concept if it has internal qualia? The "brain" comes alive with the rich structure only to disappear after the chat session is over.
Re: A Multi-Level View of LLM Intentionality
#8>Unless you think that there is some fundamental reason why LLMs will never be able to play chess competently, and I doubt there is, then it seems that we could with the right prompts implement some sort of chess AI using an LLM. You can play a good game of chess (or poker for that matter) with GPT. https://twitter.com/kenshinsamurai9/status/16625105325852917... https://arxiv.org/abs/2308.12466 There's also some work…
I've found they fall apart after a couple of moves and lose track of the game. Edit: This might not be the case anymore it seems, my below point doesn't actually contradict you, seems it matters a lot how you tell the model your moves. Also saying things like "move my rightmost pawn" completely confuses them.
The token model of LLMs doesn't map well into how human experience the world of informational glyphs. Left and right is a intrinsic quality of our vision system. An LLM has to map the idea of left and right into symbols via text and line breaks.
I do think it will be interesting as visual input and internal graphical output is integrated with text based LLMs as that should help correct their internal experience to be based closer to what we as humans experience.
Re: A Multi-Level View of LLM Intentionality
#9I'm not sure the definition of "intention" the article suggests is a useful one. He tries to make it sound like he's being conservative:
> That is, we should ascribe intentions to a system if and only if it helps to predict and explain the behaviour of the system. Whether it really has intentions beyond this is not a question I am attempting to answer (and I think that it is probably not determinate in any case).
And yet, I think there's room to argue that LLMs (as currently implemented) cannot have intentions. Not because of their capabilities or behaviors, but because we know how they work (mechanically at least) and it is incompatible with useful definitions of the word "intent."
Primarily, they are pure functions that accept a sequence of tokens and return the next token. The model itself is stateless, and it doesn't seem right to me to ascribe "intent" to a stateless function. Even if the function is capable of modeling certain aspects of chess.
Otherwise, we are in the somewhat absurd position of needing to argue that all mathematical functions "intend" to yield their result. Maybe you could go there, but it seems to be torturing language a bit, just like people who advocate definitions of "consciousness" wherein even rocks are a "little bit conscious."
Re: A Multi-Level View of LLM Intentionality
#10The authors of the text the model was trained on certainly had intentions. Many of those are going to be preserved in the output.
Can we say ChatGPT or its future versions would be like an instantiation of the Boltzmann Brain concept if it has internal qualia? The "brain" comes alive with the rich structure only to disappear after the chat session is over.
[dead]