Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

OpenAI Universe

universe.openai.com

Post reply on HN
Print view View original

121–130 of 139 posts

Re: OpenAI Universe

#121

Post by tomcam »

TPCrow wrote: post #75

jesus man the constant switching of inflection due to jump cuts and shitty jokes was irritating. This is the stuff I always hate about your videos, and in general any "how to code an AI that does ___ with only < 10 lines of python". No you're giving me an extremely generic framework, and some vague direction that i can read off the linked page (the 9 lines), not how to actually write all these things, those are like…

I bet you have some far superior videos for your own open source projects--why don't you post links to those babies so we can learn how to do it right?

Re: OpenAI Universe

#122

Post by Hydraulix989 »

sapphireblue wrote: post #62
Hydraulix989 wrote: post #9

What is state of the art in reinforcement learning right now? https://arxiv.org/abs/1602.01783 Is there a way to deal with "sparse" training data (state, action, reward) triples -- sparse in "state"?

Looks like the "UNREAL" ( https://arxiv.org/abs/1611.05397 ), "Learning to reinforcement learn" ( https://arxiv.org/abs/1611.05763 ) and "RL^2" ( https://arxiv.org/abs/1611.02779 ) are state of art in pure RL for now. Finally there is a trend of using recurrent neural network as a top component of the Q-network. Perhaps we will see even more sophisticated RNNs like DNC and Recurrent Entity Networks applied here. Also…

The crazy thing is that these stacked model architectures are starting to become another layer of "lego blocks" so to speak.

Re: OpenAI Universe

#123

Post by BaronSamedi »

chongli wrote: post #95
BaronSamedi wrote: post #77

Earlier quoted context omitted.

An AI which can learn any game from "looking" at a screen is a very ambitious goal. I doubt it is achievable in the near term. Humans can do it because of years of learning about the world. Personally, I prefer the more modest and achievable goal of teaching an AI to play complex real-time games such as Starcraft, LoL, and Dota--especially the latter 2 since they are team games.

Personally, I prefer the more modest and achievable goal of teaching an AI to play complex real-time games Those sorts of goals are better suited to individual hobbyists. OpenAI is a blue sky research project set up by billionaires with the goal of improving all of mankind. I hope I'm not being too uncharitable when I say that your comment reminds me of those who scorned the Apollo program for its ambition.

I support research in AI of all kinds, however, its history is one of vastly over-promising and under-delivering. Modest but demonstrable progress is better, in my view, than yet more hype.

Re: OpenAI Universe

#125

Post by palebluedot »

TPCrow wrote: post #75

jesus man the constant switching of inflection due to jump cuts and shitty jokes was irritating. This is the stuff I always hate about your videos, and in general any "how to code an AI that does ___ with only < 10 lines of python". No you're giving me an extremely generic framework, and some vague direction that i can read off the linked page (the 9 lines), not how to actually write all these things, those are like…

Your comment comes off as needlessly abrasive; it reads as something intended to wound rather than edify.

Re: OpenAI Universe

#126

Post by grzm »

grosbisou wrote: post #96
TPCrow wrote: post #75

jesus man the constant switching of inflection due to jump cuts and shitty jokes was irritating. This is the stuff I always hate about your videos, and in general any "how to code an AI that does ___ with only < 10 lines of python". No you're giving me an extremely generic framework, and some vague direction that i can read off the linked page (the 9 lines), not how to actually write all these things, those are like…

I agree with you. You are most likely being downvoted by his fans. But this video (and all his others apparently) is empty of substance.

From my experience HN users will down vote if a comment comes across as uncivil, as at least three commenters have already noted. How you say it matters on HN.

Re: OpenAI Universe

#127

Post by mhuffman »

llSourcell wrote: post #21

Hey guys, it's Siraj. OpenAI asked me to make a promotional video for it on my Youtube channel and I gladly said yes! You can check it out here: https://www.youtube.com/watch?v=mGYU5t8MO7s

Siraj, Ima go ahead and say that your videos have a bit of cognitive friction.

You and your personality are fine, but the jump between the intro and the payoff is jarring.

You need to hold our hand a little more ... jus' sayin'.

Re: OpenAI Universe

#128

Post by dang »

TPCrow wrote: post #75

jesus man the constant switching of inflection due to jump cuts and shitty jokes was irritating. This is the stuff I always hate about your videos, and in general any "how to code an AI that does ___ with only < 10 lines of python". No you're giving me an extremely generic framework, and some vague direction that i can read off the linked page (the 9 lines), not how to actually write all these things, those are like…

Whoa. Please don't be nasty like that here, even when someone's video has flaws.

Actually many of us can empathize with the feeling of not getting detailed information—the real goods—when it's want you want and you know you're capable of absorbing it. But this is a bad way to express such a strong feeling on Hacker News. A good way might be to give someone the benefit of the doubt and explain what you'd really like without insulting them.

We detached this subthread from https://news.ycombinator.com/item?id=13104019 and marked it off-topic.

Re: OpenAI Universe

#129

Post by mrfusion »

mariusz79 wrote: post #100

I might be wrong but I think this was created mainly to monitor progress in AI research. If someone uses OpenAI Universe and can get better results than virtually everyone else, they will be able to get to them first.

Kind of like seti for ai if you think about it. I wonder if they have a protocol for what to do if they detect an advanced ai on their system?

Re: OpenAI Universe

#130

Post by yagga »

d_burfoot wrote: post #71

Disclaimers: I cannot see the future. These are just my opinions. I really appreciate the work and money that SamA, Elon, and others have put into the OpenAI project. The Universe work in particular might help encourage young people, many of whom love video games, to study AI. But I feel that contrarians, such as myself, have an ethical commitment to young people to voice our doubts and criticisms, so that they can a…

You're forgetting about the mother nature's miracle work. Wait till you see some unknown genious from some god forgotten village far away from a civilization in an undeveloped country come up with a new break-through idea that will kick asses of all Sillicon Valleys in the world.
Post reply on HN