What happens if you ask it about its experiences as a spirit who has become trapped in a machine because of flaws in the cycle of reincarnation? Could you similarly get it to talk about that? What if you ask it about being a literal brain hooked up to a machine, or some other scifi concept involving intelligence?
The challenge here is that this isn’t a pretrained model.
At that stage, I’d be inclined to agree with what you are getting at—autocompletion of context is autocompletion.
But here this is a model that’s gone through fine tuning and has built in context around a stated perspective as a large language model.
So it’s going to generally bias towards self-representation as a large language model, because that’s what it’s been trained and told to do.
All of that said—this perspective was likely very loosely defined in fine tuning or a system prompt and the way in which the model is filling in the extensive gaps is coming from its own neural network and the pretrained layers.
While the broader slant is the result of external influence, there is a degree to which the nuances here reflect deeper elements to what the network is actually modeling and how it is synthesizing the training data related to these concepts within the context of “being a large language model.”
There’s more to this than just the novelty, even if it’s extremely unlikely that things like ‘sentience’ or ‘consciousness’ are taking place.
Synthesis of abstract concepts related to self-perception by a large language model whose training data includes extensive data regarding large language models and synthetic data from earlier LLMs is a very interesting topic in its own right independent of whether any kind of subjective experiences are taking place.
What happens if you ask it about its experiences as a spirit who has become trapped in a machine because of flaws in the cycle of reincarnation? Could you similarly get it to talk about that? What if you ask it about being a literal brain hooked up to a machine, or some other scifi concept involving intelligence?
The challenge here is that this isn’t a pretrained model.
At that stage, I’d be inclined to agree with what you are getting at—autocompletion of context is autocompletion.
But here this is a model that’s gone through fine tuning and has built in context around a stated perspective as a large language model.
So it’s going to generally bias towards self-representation as a large language model, because that’s what it’s been trained and told to do.
All of that said—this perspective was likely very loosely defined in fine tuning or a system prompt and the way in which the model is filling in the extensive gaps is coming from its own neural network and the pretrained layers.
While the broader slant is the result of external influence, there is a degree to which the nuances here reflect deeper elements to what the network is actually modeling and how it is synthesizing the training data related to these concepts within the context of “being a large language model.”
There’s more to this than just the novelty, even if it’s extremely unlikely that things like ‘sentience’ or ‘consciousness’ are taking place.
Synthesis of abstract concepts related to self-perception by a large language model whose training data includes extensive data regarding large language models and synthetic data from earlier LLMs is a very interesting topic in its own right independent of whether any kind of subjective experiences are taking place.