Live data from Hacker News

Karpathy’s Pelican

twitter.com

211–220 of 461 posts

Re: Karpathy’s Pelican

#211

IMO, the area where AI is going to be most useful over the next couple years is in developing manufacturing processes top to bottom. Maybe a million token budget is too small, but something like "design me a sneaker and all the equipment to manufacture it autonomously".

Physical reality is not software or math, LLMs can't design "equipment to manufacture autonomously".

Re: Karpathy’s Pelican

#212
post #173

Earlier quoted context omitted.

macOS covers 90% of people who would ever pay him.

This is a bizarre claim to make in this case, AI tech is used on all platforms universally.

Literally just google “mac users more likely to pay” and you will find many such instances

Re: Karpathy’s Pelican

#213

How much are the hobbit houses described in the book? The ones here look exactly like the movie

In the first paragraph (either of chapter 1 or the prologue), not at all. It's pulling everything from pre-training, so it is likely relying just as much on all the visual mediums like the Peter Jackson films, the animated The Hobbit (1977), and all kinds of random depictions of Tolkien's works.

Bilbo's house is actually described in The Hobbit and the exterior isn't really described at all in Fellowship. The prologue of Fellowship (Concerning Hobbits) mentions hobbits like round doors and windows and the fact some hobbit homes are underground, but the turf-dome design here is not mentioned. It actually mentions hobbit homes typically have bulging walls, so unless you've read the The Hobbit, you might not picture this entirely-underground style.

In The Hobbit, his home is described as a (nice) hole in "The Hill" with a perfectly round front door and round windows, which could imply the design here.

Re: Karpathy’s Pelican

#214
post #202

I’d like to see a human one shot a pelican on a bicycle in raw svg.

What do you mean by "oneshot"? The term applied to genai makes sense, but it doesn't make a whole lot of sense to apply the term to human art.

What doesn’t make sense? They aren’t drawing it by hand, they are still using SVG. Give them one chance before rendering it.

Re: Karpathy’s Pelican

#215

Earlier quoted context omitted.

Why does it require knowledge about spatial relationships?

Because the degree of realism in a video is determined by implicit knowledge of concepts like "in front of", "behind", "next to", "inside", "outside", "between", "occluded by", etc. as well as distances, angles, and the relative size of objects when viewed from a perspective.

I guess I just don't have an intuition for why that is different from what it does for non-"spatial" things. Like the fact that it works is still because it produced the code it did token by token. Whether its dealing with, e.g., "beside the rock" or "in the array", it's doing the same kind of inferential activity.

Re: Karpathy’s Pelican

#217
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.

Thank you for mentioning it and for putting your suggestion in the language you did.

That page with the time machine may not make it obvious, but the product does have a linux client!

It doesn't have the same app window and summarization of the macos version, but the transcript ingestion engine is efficient and the real value is in leveraging the database it builds using the packaged `/total-recall` or your own use of the api. (which is not yet documented but discoverable)

I am building the windows version now. I have been for the past four days. It uses a shared swift-core with the macOS and Linux versions which has been part of the reason it has taken "so long."

If anyone is on windows (or linux!) and would be willing to try it either of the clients my email is in my profile, I would be grateful.

Also I'm working up a short post with that apocolypto anim now.

Re: Karpathy’s Pelican

#218
> I also like this kind of examples because no one in their right mind would ever spend the time to write something this custom but LLMs have all the stamina and patience in the world, so it's an example where we go from "no one would ever do this" to "sure, why not, it's ~free".

Except it's not ~free, it cost ~$10. And no one in their right mind would ever exchange $10 for that crap output except in this brief moment that we're in because it's fun and surprising to see what will happen. The actual result is as close to useless as it's possible to be - it's not interesting in its own right, it's not aesthetically pleasing, nor funny, nor informative. It's just slop.

Re: Karpathy’s Pelican

#219

How much are the hobbit houses described in the book? The ones here look exactly like the movie

In the first paragraph (either of chapter 1 or the prologue), not at all. It's pulling everything from pre-training, so it is likely relying just as much on all the visual mediums like the Peter Jackson films, the animated The Hobbit (1977), and all kinds of random depictions of Tolkien's works. Bilbo's house is actually described in The Hobbit and the exterior isn't really described at all in Fellowship. The prologu…

Right, yeah I asked because I assumed it copied the look from the movie. I think it'd be more interesting to do this for something that hadn't been adapted (yet). The first chapter of Neuromancer perhaps

Re: Karpathy’s Pelican

#220
post #165
post #158

Earlier quoted context omitted.

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...

No. But it reveals something about how this technology works, its statistical properties, from which you can infer the limitations.
Post reply on HN