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

Karpathy’s Pelican

twitter.com

Post reply on HN
Print view View original

161–170 of 461 posts

Re: Karpathy’s Pelican

#161

Post by edaemon »

IsTom wrote: post #158
jmugan wrote: post #93

A lot of people are posting here about how bad the end product is, but that is kind of the point. Models have moved beyond generating images to a new kind of benchmark that better exposes understanding of the physical world, and we can use benchmarks like this to measure future progress. (Of course, it will have to be a qualitative/subjective measurement.)

Aren't they still bad at understanding how bicycle frame works? Especially the steering part?

Yes, but I think the idea here is that most models produce very similar pelicans on bicycles, so a different test might be more useful in gauging the differences in models.

Re: Karpathy’s Pelican

#162

Post by garganzol »

bredren wrote: post #8

I worked with an LLM to build a ~3D animation of the Back to the Future delorean Time Machine as a way to spice up the hero on a docs page. That took a fair amount of custom tuning and I had to create a tuning view to get some of the behaviors right. But it was enough fun that I generalized it to take in ~any scene description from a film. It goes out and gets more detailed descriptions and film stills if available b…

The product you've built the animation for is only for macOS, which is a pity cause it has a way wider appeal than macOS market share is. You have low-hanging fruits right there, don't miss them.

Re: Karpathy’s Pelican

#163

Post by timacles »

skippyfish wrote: post #24
matchagaucho wrote: post #6

It's difficult to think in exponentials. But this demonstrates we're a couple orders of magnitude away from generating 1:1 hyper-personalized entertainment and media for individuals, rather than the masses.

I very much doubt that. We now have nearly-perfect AI image generation and it hasn't really changed the nature of human expression. I don't see my friends getting wildly creative. I mostly see it used for spammy blogs, spammy books, and cringeworthy corporate marketing - basically, a negative signal, rather than "ooh, AI image, I'm in for a treat". Is your experience different? If not, what changes with moving images…

All small business marketing material now looks exactly the same.

LLMs produce an extremely small range of artistic expression, and its kind of ironic, that while it certainly looks functionally good. It immediately becomes noise because everything looks identical.

So companies are going to have to hire creatives again, in order to stand out, and be "creative"

Re: Karpathy’s Pelican

#164

Post by charcircuit »

jmugan wrote: post #93

A lot of people are posting here about how bad the end product is, but that is kind of the point. Models have moved beyond generating images to a new kind of benchmark that better exposes understanding of the physical world, and we can use benchmarks like this to measure future progress. (Of course, it will have to be a qualitative/subjective measurement.)

Bad? It has a charming style. I would watch the whole book if it was made like this.

Re: Karpathy’s Pelican

#165

Post by gegtik »

IsTom wrote: post #158
jmugan wrote: post #93

A lot of people are posting here about how bad the end product is, but that is kind of the point. Models have moved beyond generating images to a new kind of benchmark that better exposes understanding of the physical world, and we can use benchmarks like this to measure future progress. (Of course, it will have to be a qualitative/subjective measurement.)

Aren't they still bad at understanding how bicycle frame works? Especially the steering part?

Maybe that makes them human..

https://www.booooooom.com/2016/05/09/bicycles-built-based-on...

Re: Karpathy’s Pelican

#166

Post by zh3 »

IsTom wrote: post #158
jmugan wrote: post #93

A lot of people are posting here about how bad the end product is, but that is kind of the point. Models have moved beyond generating images to a new kind of benchmark that better exposes understanding of the physical world, and we can use benchmarks like this to measure future progress. (Of course, it will have to be a qualitative/subjective measurement.)

Aren't they still bad at understanding how bicycle frame works? Especially the steering part?

Shhh...you'll alert the models :)

Totally agree though, anyone with a vague understanding of how bikes works ignores the pelican because they know the bike is unrideable in the first place.

Re: Karpathy’s Pelican

#167

Post by peterleiser »

abletonlive wrote: post #154
HarHarVeryFunny wrote: post #47

It seems pretty clear that Anthropic models have been specifically trained to be good at generating three.js (JavaScript 3-D Graphics) code, so given current state of AI code generation in general, I don't find three.js models/animations as indicative of anything other than the model's ability to write three.js code. When Fable was first released the day-1 demos of it on Twitter (presumably from people who were given…

[flagged]

But LLM's passed the Turing test, so we're done, right? ;-) Seriously, though, I agree with you that people keep moving the ball.

Re: Karpathy’s Pelican

#168

Post by fasterik »

barrenko wrote: post #124

This has started to feel a bit like the beginning of railroads and then the steampunk fiction of "let's just build railroads to everywhere". We don't need it and there's no use for it. As with painting, after a while there's nothing really new to paint, we genuinely need 0 new software. We need to fix our broken physical world, our social lives, our kids and what's left of our democracies. This software crap is done,…

Agreed that software isn't going to fix our institutions. But we need 0 new software? AlphaFold won its creators a Nobel prize in chemistry and solved a research problem that feeds into every area of biology, medical research, and drug discovery. We still have an untold number of unsolved problems related to human health, food production, energy production, infrastructure, transportation, education... The list is practically infinite.

Re: Karpathy’s Pelican

#169

Post by QuantumNomad_ »

throwaway27448 wrote: post #37
QuantumNomad_ wrote: post #17

Earlier quoted context omitted.

It was open sourced as Apache Wave when Google shut it down. Years later Apache moved it to read only because of low community activity. The archived git repo on GitHub remains available to clone and revive as a fork. https://github.com/apache/incubator-retired-wave

This doesn't explain the lack of marketing. Apache isn't exactly known for pushing tech. Google never tried to improve on gmail.

Sorry if it wasn’t clear, I was adding this info for context and for anyone who hopefully feels inspired to pick up Wave and make something from it given that it was all open sourced and all. And I figured that in the chain after your comment about it having been useful looking all along was a natural place to add this additional info and link.

Re: Karpathy’s Pelican

#170

Post by siliconc0w »

There is a tipping point between procedurally generating everything in SVG to maybe giving them tool access to something like 3dsmax (or having them build and then use a tool to do the thing vs doing the thing).
Post reply on HN