Live data from Hacker News

Tinygrad

github.com

121–130 of 159 posts

Re: Tinygrad

#121

I'd like to ship a video game that does machine learning and trains on its experiences with the player. Yes, I know there are many potential problems with this. What is the best way to ship training code in a game? Do I embed Python and PyTorch or something? Do I code my own NN training algorithm? Do I use a library such as Tinygrad?

If your game has enemies, you could give each unit its own brain. Behind the scenes you could have a "gene pool". When a unit dies it's removed from the pool. When it performs well (eg. damages player or wins the game) the unit can reproduce. Then you add the usual stuff (mutate parameters, cross-breeding fittest units).

For training you could just make two AI teams play against each other (off the cuff, 10-100k games should do the trick). Once you release the game, you could sample the best AI from each player's machine. Free distributed neuroevolution cluster ;)

I've wanted to do this for a while but I haven't made any proper games yet. Someday!

Re: Tinygrad

#122
post #68
post #61

Earlier quoted context omitted.

I don't know. I ran the idea of purposely getting addicted to opioids to see if i can quit by my wife and she assured me i was crazy.

This direction goes off-topic, but: look, if you married her, -- either you go along well, hence that she agrees with your opinion is a weak test; -- or you married her to test yourself, which would prove my point. TND; QED. /J

Maybe she married him to test herself?

Re: Tinygrad

#123
post #14

I like this guy mostly for preserving a hacker-ish culture in the atmosphere and for just being a real human being in public. Too often do I feel like I'm just interacting with interfaces to corporations or people who self censor themselves so much they barely feel human. I'm not sure this library matters much to me but I maintain positive perspective on this guy for these reasons.

Having gone to college and knowing this guy personally from then, you would have a much different opinion... Maybe he has grown up, but back then... yeeesh

Maybe you were the one who sucked.

Re: Tinygrad

#124
post #61

Earlier quoted context omitted.

I don't know. I ran the idea of purposely getting addicted to opioids to see if i can quit by my wife and she assured me i was crazy.

I'm in a similar situation, but not with opioids. I don't think that this is a crazy idea at all. We're just testing our limits and seeing if we as smart as we say.

And what if you aren’t?

Re: Tinygrad

#125

I'd like to ship a video game that does machine learning and trains on its experiences with the player. Yes, I know there are many potential problems with this. What is the best way to ship training code in a game? Do I embed Python and PyTorch or something? Do I code my own NN training algorithm? Do I use a library such as Tinygrad?

I think video games already do this; video game AI existed before deep learning, it just used things like decision trees and MCMC.

Re: Tinygrad

#126
post #109

Earlier quoted context omitted.

The detailed follow-up to that post is here: https://geohot.github.io/blog/jekyll/update/2021/12/12/a-cor...

Interesting! I think Cerebras is exciting too, the problem is that it's so expensive that there will never be a software ecosystem for it. The people who would develop it will never have access to one.

Yep, it's hard to see how Cerebras will ever have much of an ecosystem, since hardware makers are traditionally not very good at building and maintaining one by themselves. But they're probably aiming at very specialized customers only.

Geohot is right about the AI accelerator market's problems, and a competitive 4-digit-dollars device is a great idea even if his initial strategy was way off. Although you could say almost the same thing about the high-performance CPU and GPU duopolies (Apple's chips don't count due to their proprietary OS lock-in, although I wish Asahi Linux luck at fixing that).

[edit] And beyond that, you have TSMC dominating the next-gen fab market, too.

Re: Tinygrad

#127
post #95
post #86

Even more tiny: https://github.com/breandan/picograd/blob/main/picograd.py

Look man, this is just too tiny. People are upset in this thread about the excessively short line count of OP as it is. What is this, some sort of autograd for ants? It is freaking me out, remove this link.

Lol

Re: Tinygrad

#128
post #81

Earlier quoted context omitted.

("Tertium Non Datur" - that analyzed options are exhaustive)

Meaning this only neutrally, and completely respectfully: have you considered that you're a bit abnormal as well?

The only normal people are the ones faking it

Re: Tinygrad

#129
post #65

Earlier quoted context omitted.

Everyone should kill their heroes. They almost never live up to the pedestals people place them on. They are all just people and have flaws. They don’t have to be some perfect person to do cool things we can respect.

I respect geohotz' achievements (generally). I would never hold him up as an example of hacker culture, or his persona as one to emulate. There is a difference between these things.

Out of curiosity who would you show as an example of hacker culture?

Re: Tinygrad

#130
post #14

I like this guy mostly for preserving a hacker-ish culture in the atmosphere and for just being a real human being in public. Too often do I feel like I'm just interacting with interfaces to corporations or people who self censor themselves so much they barely feel human. I'm not sure this library matters much to me but I maintain positive perspective on this guy for these reasons.

I wish Dang would just kill this sub-thread. What a mess.

A whole amateur dissection of this guy's personality. It's so bloody awkward, just comment on the work and move on.

But it's great to know HN readers are all such paragons of virtue.

Post reply on HN