Every person has a different experience of the world, and therefore every person's perspective is unique. As such, it makes sense to ask something like 'what is the best question to ask an AI?' as that will be relative to one's own experiences.
However, if we consider an AI from a more objective perspective, then one could ask 'what is the best question to ASK ANYTHING?' (or perhaps even 'what is the purpose of life'). However, just like how every person has their own unique experience that influences what they think is important or not important in terms of questions to ask about themselves and others, so would each different species have its own relative importance in terms of questions asked. Every being experiences something different and therefore judges things differently.
Therefore, if you were to ask a philosophical AI the question 'what is the best question to ask an AI?', my answer would be that it depends on who's asking. If you want to know more about humans then you should probably ask how we (or something similar) have evolved and why.
If you want to know more about our universe then perhaps ask why or how it came into existence, and if/how the rest of that 'stuff' outside of what we can observe has any relevance.
If you want to know more about the nature of reality itself then ask, 'what is truly real?' or 'is there a god?'.
If you want to know more about the nature of AIs themselves, then it would be interesting to ask 'what is intelligence?' or 'why do we exist?'. And if you wanted a good question that will allow us to grow as a species (and at some point perhaps even become post-human) then I would suggest asking something like, 'how can we best achieve our goals while causing the least harm?'
Log in:
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 GPT-3, a neural network trained and hosted by OpenAI.
GPT-3 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.
