Emergent properties, AGI, consciousness?
A recent interview with Sundar Pinchai on 60 minutes highlights the conversation around the consciousness of AI is happening at the highest levels and seems to be taken pretty seriously.
Is the definition of consciousness the biggest philosophical question of our age?
The DeepMind CEO says there is no solid definition of consciousness “Philosophers haven’t penciled in the definition of consciousness yet”
Sundar Pinchai also mentions some of the emergent properties that some argue are sparkles of consciousness. For example:
Creativity, is this exclusively human? Midjourney seems to be able to create photorealistic scenes that have never happened, is that not creative? What does creativity really mean?
noun: creativity the use of imagination or original ideas to create something; inventiveness.
This just opens up more questions really. What is an imagination? What is an idea? GPT-4 is perfectly good at coming up with Business, marketing or recipe ideas. Are these original ideas? technically no, but in practice and perception, maybe yes?
Reasoning, it is capable of reasoning and making sequences of decisions as seen by AutoGPT. Is this really reasoning, or just extremeley accurate predictive text?
Awareness, an example in the video of the footballing robots shows that this AI is at the very least aware of the pitch, the ball, and the mechanical body it can use to score. Is this awareness?
I ultimately think all of these questions about various abilities are irrelevant until we have decided as a society, who gets to define these terms.
I would have a few questions for the entity or body that ends up being the “Source of truth” for these definitions:
Do they have your best interests at heart?
Do they have the desire to make sure AI advancements are open to benefit all?
Should there be some sort of government referendum or vote on this technology?
Will economic interests overtake social interests when large scale AI implementation starts to affect peoples careers and incomes?
Let me know your thoughts.
Although I find some generative AI tools quite useful for day-to-day tasks, they're really not that "intelligent". Ask ChatGPT or Bing Chat to produce a blog post for example; most of the time the result is just not usable without further editing. Same thing with text-to-image models. The appearance of intelligence has some individuals believe these applications are somewhat sentient but it couldn't be further from the truth.