To expound, this just seems like a power grab to me, to "lock in" the lead and keep AI controlled by a small number of corporations that can afford to license and operate the technologies. Obviously, this will create a critical nexus of control for a small number of well connected and well heeled investors and is to be avoided at all costs.
It's also deeply troubling that regulatory capture is such an issue these days as well, so putting a government entity in front of the use and existence of this technology is a double whammy — it's not simply about innovation.
The current generation of AIs are "scary" to the uninitiated because they are uncanny valley material, but beyond impersonation they don't show the novel intelligence of a GPI... yet. It seems like OpenAI/Microsoft is doing a LOT of theater to try to build a regulatory lock in on their short term technology advantage. It's a smart strategy, and I think Congress will fall for it.
But goodness gracious we need to be going in the EXACT OPPOSITE direction — open source "core inspectable" AIs that millions of people can examine and tear apart, including and ESPECIALLY the training data and processes that create them.
And if you think this isn't an issue, I wrote this post an hour or two before I managed to take it live because Comcast went out at my house, and we have no viable alternative competitors in my area. We're about to do the same thing with AI, but instead of Internet access it's future digital brains that can control all aspects of a society.
Although I assume if he’s speaking on AI they actually intend on considering his thoughts more seriously than I suggest.
If this is so, and given the concrete examples of cheap derived models learning from the first movers and rapidly (and did I mention cheaply) closing the gap to this peak, the optimal self-serving corporate play is to invite regulation.
After the legislative moats go up, it is once again about who has the biggest legal team ...
Recent developments in AI only further confirm that the logic of the message is sound, and it's just the people that are afraid the conclusions. Everyone has their limit for how far to extrapolate from first principles, before giving up and believing what one would like to be true. It seems that for a lot of people in the field, AGI X-risk is now below that extrapolation limit.
Maybe it'll turn out to be a distinction that doesn't matter but I personally still think we're a ways away from an actual AGI.
if you had described GPT to me 2 years ago I would have said no way, we're still a long way away from a machine that can fluidly and naturally converse in natural language and perform arbitrary logic and problem solving, and yet here we are.
I very much doubt that in 5 years time we'll be talking about how GPT peaked in 2023.
In fact, it has been so thoroughly solved that anyone can download an open-source solution and run it on their computer.
And yet, the general reaction of most people seems to be, "That's kind of cool, but why can't it also order me a cheeseburger?"
I generated this just now:
Me: Jack and Jill are sitting next to each other in a room. There is no one else in the room. The person sitting next to Jack is sad. The person sitting next to Jill is angry. Who is sad, Jack or Jill?
GPT4: Based on the information provided, it is not possible to determine who is sad and who is angry, as there is a contradiction in the given statements. If Jack and Jill are the only ones in the room and sitting next to each other, then the person sitting next to Jack would be Jill and the person sitting next to Jill would be Jack. The statements about their emotions conflict with each other, so it is not possible to accurately determine who is sad or angry.