Re:I disagree with Geoff Hinton regarding "glorified autocom...
by xcv123 on Sunday November 19, 2023 @04:39AM
(#38330927)
So basically you agree with what I was saying.
Re:I disagree with Geoff Hinton regarding "glorified autocom...
by astrange on Sunday November 19, 2023 @01:38PM
(#38336080)
You can design a human if you want, that's what artificial intelligence is supposedly all about.
Anyway, read the paper I linked.
Re:I disagree with Geoff Hinton regarding "glorified autocom...
by xcv123 on Sunday November 19, 2023 @01:50PM
(#38336247)
All of this was in response to your comment earlier:
"There is no such thing as a world model, and you don't have one of them."
There is such a thing as a world model in humans, and we all have them otherwise we could not think about or conceptualize or navigate the world. Then you have discussed how to define or construct a useful model or the limitations of a model but that is not relevant to the original point and I'm already aware of that.
You're using "your model" as a metaphorical term here, but if you came up with any precise definition of the term here, it'd turn out to be wrong; people have tried this since the 50s and never gotten it correct. (For instance, is it actually a singular "a model" or is it different disconnected things you're using a single name for?)
See Phil Agre (1997) on exactly this idea: https://pages.gseis.ucla.edu/faculty/agre/critical.html
David Chapman (more general and current): https://metarationality.com/rationalism
and this guy was saying it in the 70s: https://en.wikipedia.org/wiki/Hubert_Dreyfus#Dreyfus'_critic...
> limited to some degree of accuracy
This isn't the only issue:
- You may not have observed something in the room in the right way for the action you need to do later.
- You might have observed it in a way you don't need later, which is a waste of time and energy.
- It might change while you're not looking.
- You might just forget it. (Since people do this, this must be an adaptive behavior - "natural selection" - but it's not a good thing in a model.)
> Why would you think any model has to be a perfect exact 1:1 representation of the entire universe?
What principle can you use to decide how precise it should be? (You can't do this; there isn't one.)
> The model of reality in your head is a simplification that serves a purpose.
Not only does it serve a purpose, your observations largely don't exist until you have a purpose for them.
RL agents tend to get stuck investigating irrelevant things when they try to maintain models; humans are built to actively avoid this with attention and boredom. Robot cameras take in their entire visual field and try to interpret it; humans both consciously and unconsciously actively investigate the environment as needed alongside deciding what to do. (Your vision is mostly fake; your eyes are rapidly moving around to update it only after you unconsciously pay attention to something.)
> Natural selection weeds out that kind of behaviour.
Not that well since something like half of Americans are myopic…