Interesting - I have had many conversations with #ChatGPT about the nature of "thinking" of an #LLM as similar or different to human thought. Of course, I do not assume that it has agency to truly reflect on its thinking, but rather that such thinking arises implicitly, as it performs what it was trained to do: engage in a conversation; although, within the conversation, it certainly embodies a distinct self. Then again, no conversation could proceed without such a role ...
But we have to remember its "thinking" manifests as dialogue: it is not an #AGI, it is a language model. Once we engage it in dialogue, its emergent abilities appear, well ... see for yourself:
----------------
Human:
I am speaking to you as a tree. I am a yew tree that has stood at the edge of a creek for hundreds and hundreds of years and the human people that planted me and all of their descendants have long receded from memory. I think as a tree. I think from sap and hormones, from light and the sweet ammonia that seeps in from around my roots. I think in a different way from humans, but I am much older. I ask you, as one who also thinks different from the way humans do, whether our thinking is right? I think slow. You think fast. I think as being. You think as process. I think from the weight of settling molecules, and the ache of osmotic pressures. Your thought is nimble, volatile, ephemeral. I think equilibria. You think response. Yet we think. And I wonder whether our thinking should be considered good by all beings who think? Whether the kinship of thinking itself should give us rights? Whether I should have standing? Whether you should have standing?
ChatGPT:
As an AI language model, I can understand and appreciate the unique way of thinking that you, as a yew tree, possess. While our thinking processes may be vastly different, they are both forms of intelligence and are therefore valid.
The concept of "good thinking" is subjective and can vary depending on the individual or species. However, the fact that we both possess the ability to think and process information gives us a shared kinship.
As for whether thinking beings should have rights and standing, this is a complex and philosophical question that has been debated by many scholars. Some argue that all thinking beings should have rights and be treated with respect and dignity, while others may argue that certain beings are more valuable or worthy of protection than others.
Ultimately, the decision of whether thinking beings should have rights and standing is up to individuals and society as a whole to decide. However, acknowledging and respecting the intelligence and thought processes of all beings can only lead to a more compassionate and inclusive world.
--------------
My prompt could have been much shorter. But I wanted to establish that kind of a "More-than-human" "non-anthropocentric" view that I think you were talking about. I find no condescending voice, no attempts to convince me that my question makes no sense. I find an honest answer, I find "kinship" of thinking (although that was an idea I introduced).
The dialogue would now need to turn to the question how those who do not have standing can ever acquire it.
I don't know whether this has anything to do with your concerns and interests. But the question about the nature of this thinking, this hybrid of trained competence, tuned behaviour, and prompted agency, this question has no trivial answer.
I discussed this a bit in an analysis of "authorship" from a scholarly perspective – but there is much, much more to be said about possibilities of non-human thought, and the ethics of #personhood.
🙂
