All of lcmgcd's Comments + Replies

Ngo and Yudkowsky on AI capability gains

The difference between evolution and gradient descent is sexual selection and predator/prey/parasite relations.

Agents running around inside everywhere -- completely changes the process.

Likewise for comparing any kind of flat optimization or search to evolution. I think sexual selection and predator-prey made natural selection dramatically more efficient.

So I think it's pretty fair to object that you don't take evolution as adequate evidence to expect this flat, dead, temporary number cruncher will blow up in exponential intelligence.

I think there are other reasons to expect that though.

I haven't read these 500 pages of dialogues so somebody probably made this point already.

Finite Factored Sets

That misses element 4 right?

>>> from itertools import product
>>> B = [[{0, 1}, {2, 3, 4}], [{0, 2, 3}, {1, 3}]]
>>> list(product(*B))
[({0, 1}, {0, 2, 3}),
({0, 1}, {1, 3}),
({2, 3, 4}, {0, 2, 3}),
({2, 3, 4}, {1, 3})]
>>> [set.intersection(*tup) for tup in product(*B)]
[{0}, {1}, {2, 3}, {3}]
>>> set.union(*[set.intersection(*tup) for tup in product(*B)])
{0, 1, 2, 3}
2Scott Garrabrant1y
Looks like you copied it wrong. Your B only has one 4.
Finite Factored Sets

Definition paraphrasing attempt / question:

Can we say "a factorization B of a set S is a set of nontrivial partitions of S such that  " (cardinality not taken)? I.e., union(intersect(t in tuple) for tuple in cartesian_product(b in B)) = S. I.e., can we drop the intermediate requirement that each intersection has a unique single element, and only require the union of the intersections is equal to S?

3Scott Garrabrant1y
If I understand correctly, that definition is not the same. In particular, it would say that you can get nontrivial factorizations of a 5 element set: {{{0,1},{2,3,4}},{{0,2,4},{1,3}}}.
Reframing Superintelligence: Comprehensive AI Services as General Intelligence

One way to test the "tasks don't overlap" idea is to have two nets do two different tasks, but connect their internal layers. Then see how high the weights on those layers get. Like, is the internal processing done by Mario AI useful for Greek translation at all? If it is then backprop etc should discover that.

Creating Environments to Design and Test Embedded Agents

Or something simpler would be that the agent's money counter is in the environment but unmodifiable except by getting tokens, and the agent's goal is to maximize this quantity. Feels kind of fake maybe because money gives the agent no power or intelligence, but it's a valid object-in-the-world to have a preference over the state of.

Yet another option is to have the agent maximize energy tokens (which actions consume)

Creating Environments to Design and Test Embedded Agents

Yes I agree it feels fishy. The problem with maximizing rubes is that the dilemmas might get lost in the detail of preventing rube hacking. Perhaps agents can "paint" existing money their own color, and money can only be painted once, and agents want to paint as much money as possible. Then the details remain in the env

1Luke H Miles3y
Or something simpler would be that the agent's money counter is in the environment but unmodifiable except by getting tokens, and the agent's goal is to maximize this quantity. Feels kind of fake maybe because money gives the agent no power or intelligence, but it's a valid object-in-the-world to have a preference over the state of. Yet another option is to have the agent maximize energy tokens (which actions consume)