Wolfram: Computational equivalence prevents shortcutting complex system predictions
Stephen Wolfram · All-In Summit: Stephen Wolfram on computation, AI, and the nature of the universe · Oct 26, 2023 · at 12:53
Stephen Wolfram explains computational irreducibility and why predictive models cannot shortcut complex natural computations.
0:00 / 0:17exact quote · 17.9s
▶ Watch the full episode on YouTube → 720p mp4 · rendered on demand · StarZero watermark
“So this principle of computational equivalence says, whether you have a brain or a computer or mathematics or statistics or whatever else, you are really just equivalent in your computational sophistication to the system that you're trying to predict. And that's why you can't make that prediction. That's why computational irreducibility happens.”
quote is from the automated transcript, cleaned for reading: filler sounds and stutters are removed, nothing is rephrased. names can be misheard (the analysis reads context, assessments check outside sources). how →
More from Stephen Wolfram
Wolfram: Space is discrete and composed of fundamental atoms
“Space is discrete. There are atoms of space, so to speak, not like physical atoms like hydrogen, helium, and things.”
Wolfram: Time is a computational process of network rewriting
“Time is a computational phenomenon. Time is the progressive change of the network.”
Wolfram: Space-time and gravity arise from computationally bounded observers
“And it turns out that exact same phenomenon is the origin of space-time and gravity, that these, all these atoms of space operating in this network, it's all this computationally irreducible process, but observers like us, observers who are computationally bou…”
Wolfram: Maximizing AI capability requires accepting unexpected behavior
“So we kind of have this trade off. We either can understand what's going to happen, in which case we don't let our AIs really do what they can do, or we always say, okay, we're going to run the risk of the AI doing something unexpected.”