There is no such thing as general intelligence, i.e. an algorithm that is “capable of behaving intelligently over many domains” if not specifically designed for these domain(s). As a corollar, AI will not go FOOM. (80% confident)
EDIT: Quote from here
Yes!
Humans are “designed” to act intelligently in the physical world here on earth, we have complex adaptations for this environment. I don’t think we are capable of acting effectively in “strange” environments, e.g. we are bad at predicting quantum mechanical systems, programming computers, etc.
No, I don’t think I would be capable if the domain is sufficiently different from the EEA.
I’m not sure what your point is, I don’t think I use the term “algorithm” in a non-standard way.
Wikipedia says: “Thus, an algorithm can be considered to be any sequence of operations that can be simulated by a Turing-complete system.”
When talking about “intelligence” I assume we are talking about a goal-oriented agent, controlled by an algorithm as defined above.
I understand “capable of behaving intelligently” to mean “capable of achieving complex goals in complex environments”, do you disagree?
This is of course a matter of degree, but basically yes!
I understand the concept of recursive self-optimization und I don’t consider it to be very implausible.
Yet I am very sceptical, is there any evidence that algorithm-space has enough structure to allow for effective search to allow such an optimization?
I’m also not convinced that the human mind is good counterexample, e.g. I do not know how much I could improve on a the sourcecode of a simulation of my brain once the simulation itself runs effectively.
I’ll try to give examples:
For computer programming: Given a simulation of a human brain, improve it so that the simulated human is significantly more intelligent.
For quantum mechanics: Design a high-temperature superconductor from scratch.
Are humans better than brute-force at a multi-dimensional version of chess where we can’t use our visual cortex?
Not a good start if we are facing exponential search-spaces! If brute-force would work, I imagine the AI-problem would be solved?
Please give evidence that “a more impressive kind of general intelligence” actually exists!
Finding evidence for something is easy but isn’t the sort of habit I like to encourage in myself.
My intention was merely to point out where I don’t follow your argument, but your criticism in my formulation is valid.
“More impressive than humans” is a ridiculously low bar.
I agree, we can probably build far better problem-solvers for many problems (including problems of great practical importance)
algorithm that can in principle handle most any problem, given unlimited resources
My concern is more about what we can do with limited ressources, this is why I’m not impressed with the brute-force-solution
Even being able to construct ways to brute force stuff and tell whether the brute force solution is in fact a solution is possibly a more difficult thing to find in algorithm space than optimisations thereof.
This is true, I was mostly thinking about a pure search-problem where evaluting the solution is simple. (The example was chess, where brute-forcing leads to perfect play given sufficient ressources)
Have you checked if your friends actually know statistical physics? Maybe they only know the thermodynamic concept of entropy, which could seem quite different from the information theoretic entropy.
This book explains at the beginning why entropy is not a measure for disorder, which seems to be a common misconception among physicists.
The reason for this is the compatibility of the blood types, for example O-negative-blood can be donated to everyone and is therefore used in emergencies where the blood type of the recipient is not known.
I believe there is a straightforward way: Consider bets on events with known probability!
If you really want to enjoy exercising more, find a sport you enjoy.
In my experience, this solves the problem of motivation completely. Try out something that is new and interesting in itself, different from past negative experiences, and do it simply because it’s fun, without feeling an obligation to “exercise” or “stay fit”.
Possible second step: Set up a prediction market.
I downvoted your post because I believe the flaw in your argument, as pointed out by jsteinhardt, is pretty obvious.
If researchers are more likely to work on problems they find interesting, we will automatically find that most of the useful research was done by people who found it interesting. We will also find that there is a lot of useless research being done.
I think this is obviously the case, and the data therefore does not give evidence to the hypothesis that interestingness is a good heuristic for usefulness.
One small correction:
The last part of this sentence should probably be “that candidates we don’t like are(!) qualified.”