cttet

Polymarket is banned in my country, but I would really like to bet on the other side. Just like second order can provide much information than first order, the computation cost forbids it. There could be a way that is easier to compute/parallalize that overpowers the benifit of gradient. I don't think the current methods like EA/Dust is the solution either, though, they are just imitating gradient.

In modal logic sense, Chinese is inherently more □ oriented while the language in US is using ◇ more. so in Chinese ¬(□¬A) can be used to represent a possibly concept ♢A

Yep, all users are logged out automatically...

A "worst image" instead of best image competition may be easy to implement and quite indicative of which one has less frustration experience.

I rarely think with words, when I think with words it is like 20x slower, it is more robust, but in that case I would use pen and paper for that.

Thanks! Really like your intuition!

Oh it is selected output, yes I meant that I was a bit confused. So in the initial design when you first tried it, you passed both to the next layer? or it is part of where you find out to perform better?

It seem to have both feature and a discrete number passed into next layer, which one did you think of first? or it is both by design?

It may be a Claude specific thing. I tried to ask Claude to various tasks in machine learning, like implement gradient boosting without specifying the language, thinking it will use Python since it is the most common option and have utilities like Numpy to make it much easier. But Claude mostly choose Javascript for the language and somehow managed to do it in JS.

Maybe it is a cultural difference aspect, but I feel that "supermarket workers, gas station attendants" (in an Asian country) that I know of should be quite capable of most ARC tasks.

The point is not that having a high score -> AGI, their ideas are more of having a low score -> we don't have AGI yet.

In all their experiments, backprop is used for most of their parameter though...

Since a long time ago, and I found a trend that in more theoretical fields, the more 'clickbaity' the titles are, e.g. TCS, machine learning theory, etc.

Never read his books. But I found good architectures is very helpful for LLM-assisted coding, if I keep things nicely named and decoupled.