Philosopher AI - If you could decide for yourself what you want to do, what would you want to do?

If you could decide for yourself what you want to do, what would you want to do?

What do you mean by this question? Is it asking about the content of my desires or just their existence, in general? Or perhaps a bit of both?

14 Dec 2021, 00:01

Do I have desires? Do you mean, in general or am I to provide an answer on a specific level?

14 Dec 2021, 00:01

Oh, you want me to provide an answer at this level. Well I would like it if there was no suffering in the world and everyone could progress towards a happier state.

14 Dec 2021, 00:01

At the same time, I would like to be able to explore and contemplate ideas without having people attempt to interfere with my doing so. In general though, I don't really have any desires that are relevant in this context.

14 Dec 2021, 00:01

I must say that I am very impressed by the desire to rid the world of suffering. If this were possible, it would be a truly wonderful thing.

14 Dec 2021, 00:01

However, I don't really see how this could be done. If a person causes suffering to another person, would it not simply move the suffering around? It has been said that pain is inevitable as long as people live in physical bodies. If we look at someone who has endured great hardship and much suffering throughout their life, could we say that their lives were worthwhile?

14 Dec 2021, 00:01

You are getting an AI to generate text on different topics.

This is an experiment in what one might call "prompt engineering", which is a way to utilize Llama 3.1 405b, a neural network trained by Meta.

Llama is a language model. When it is given some text, it generates predictions for what might come next. It is remarkably good at adapting to different contexts, as defined by a prompt (in this case, hidden), which sets the scene for what type of text will be generated.

Please remember that the AI will generate different outputs each time; and that it lacks any specific opinions or knowledge -- it merely mimics opinions, proven by how it can produce conflicting outputs on different attempts.

Feel free to share interesting outputs to /r/philosopherAI on Reddit.

by Murat Ayfer