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

Apple Releases Open Weights Video Model

starflow-v.github.io

Post reply on HN
Print view View original

161–170 of 178 posts

Re: Apple Releases Open Weights Video Model

#161

Post by VogonPoetry »

kkylin wrote: post #95
densh wrote: post #7

Earlier quoted context omitted.

> As a blind person, AI has changed my life. Something one doesn't see in news headlines. Happy to see this comment.

Like many others, I too would very much like to hear about this. I taught our entry-level calculus course a few years ago and had two blind students in the class. The technology available for supporting them was abysmal then -- the toolchain for typesetting math for screen readers was unreliable (and anyway very slow), for braille was non-existent, and translating figures into braille involved sending material out to…

I did a maths undergrad degree and the way my blind, mostly deaf friend and I communicated was using a stylized version of TeX markup. I typed on a terminal and he read / wrote on his braille terminal. It worked really well.

Re: Apple Releases Open Weights Video Model

#162

Post by kkylin »

VogonPoetry wrote: post #161
kkylin wrote: post #95

Earlier quoted context omitted.

Like many others, I too would very much like to hear about this. I taught our entry-level calculus course a few years ago and had two blind students in the class. The technology available for supporting them was abysmal then -- the toolchain for typesetting math for screen readers was unreliable (and anyway very slow), for braille was non-existent, and translating figures into braille involved sending material out to…

I did a maths undergrad degree and the way my blind, mostly deaf friend and I communicated was using a stylized version of TeX markup. I typed on a terminal and he read / wrote on his braille terminal. It worked really well.

Thanks! Did you communicate in "raw" TeX, or was it compiled / encoded for braille? Can you point me at the software you used?

Re: Apple Releases Open Weights Video Model

#163

Post by travisjungroth »

gostsamo wrote: post #55
travisjungroth wrote: post #46

Earlier quoted context omitted.

It might be that you’re not perfectly clear on what exactly you’re trying to convey with the image and why it’s there.

sorry, snark does not help with my desire to improve accessibility in the wild.

I really didn’t mean to be snarky. Maybe if I was speaking, my tone would have made that more clear, or I could have worded it differently.

“Why is this here? What am I trying to say?” are super important things in design and also so easy to lose track of.

Re: Apple Releases Open Weights Video Model

#164

Post by travisjungroth »

hrimfaxi wrote: post #63
travisjungroth wrote: post #46

Earlier quoted context omitted.

It might be that you’re not perfectly clear on what exactly you’re trying to convey with the image and why it’s there.

What would you put for this? "Graph of All-Transactions House Price Index for the United States 1975-2025"? https://fred.stlouisfed.org/series/USSTHPI

Charts would have a link to tabular data. It’s the “business illustrations” that are more about understanding purpose.

Re: Apple Releases Open Weights Video Model

#165

Post by astrange »

asadotzler wrote: post #153
andy_ppp wrote: post #104

Earlier quoted context omitted.

I wonder if there's anything that can help blind people to navigate the world more easily - I guess in the future AR Glasses won't just be for the sighted but allow people without vision to be helped considerably. It really is both amazing and terrifying the future we're heading towards.

AURA Vision for blind and low vision people has been doing this for years. Be My Eyes has been doing this for years without AI. Meta Ray-Bans can do this. There's nothing new coming soon that hasn't already been available for a while, only refinements.

This is an area where a difference in degree becomes a difference in kind quite easily. If an AI is telling you what it's looking at, it suddenly means a lot more once it… knows what it's looking at.

Re: Apple Releases Open Weights Video Model

#166

Post by astrange »

whywhywhywhy wrote: post #136
justinclift wrote: post #36

Earlier quoted context omitted.

> in-house stock video dataset Wonder if "iCloud backups" would be counted as "stock video" there? ;)

More likely AppleTV shows

Stock video means stock video.

https://en.wikipedia.org/wiki/Stock_photography

Re: Apple Releases Open Weights Video Model

#167

Post by pabs3 »

limagnolia wrote: post #143
RobotToaster wrote: post #15

The license[0] seems quite restrictive, limiting it's use to non commercial research. It doesn't meet the open source definition so it's more appropriate to call it weights available. [0] https://github.com/apple/ml-starflow/blob/main/LICENSE_MODEL

They haven't even released the weights yet... As for the license, happily, Model Weights are the product of machine output and not creative works, so not copyrightable under US law. Might depend on where you are from, but I would have no problem using Model Weights however I want to and ignoring pointless licenses.

The output of a compiler is copyrightable, why aren't models similarly copyrightable?

Re: Apple Releases Open Weights Video Model

#168

Post by pabs3 »

Aloisius wrote: post #154
limagnolia wrote: post #144

Earlier quoted context omitted.

I think you are looking at the code license, not the model license.

No, it's the model license. There's a second license for the code. Of course, model weights almost certainly are not copyrightable so the license isn't enforceable anyway, at least in the US. The EU and the UK are a different matter since they have sui generis database rights which seemingly allows individuals to own /dev/random.

The output of a compiler is copyrightable, why aren't models similarly copyrightable?

Re: Apple Releases Open Weights Video Model

#169

Post by devinprater »

chrisweekly wrote: post #89
tippa123 wrote: post #19

Earlier quoted context omitted.

+1 and I would be curious to read and learn more about it.

Same! @devinprater, have you written about your experiences? You have an eager audience...

I suppose I should write about them. A good few will be about issues with the mobile apps and websites for AI, like Claude not even letting me know a response is available to read, let alone sending it to the screen reader to be read. It's a mess, but if we blind people want it, we have to push through inaccessibility to get it.

Re: Apple Releases Open Weights Video Model

#170

Post by devinprater »

kulahan wrote: post #151
devinprater wrote: post #147

Earlier quoted context omitted.

Mainly realtime processing. I play video games, and would love to play something like Legend of Zelda and just have the AI going, then ask it "read the menu options as I move between them," and it would speak each menu option as the cursor moves to it. Or when navigating a 3D environment, ask it to describe the surroundings, then ask it to tell me how to get to a place or object, then it guide me to it. That could be…

Weird question, but have you ever tried text adventures? It seems like it's inherently the ideal option, if you can get your screen reader going.

Yep, they're nice. There are even online versions.
Post reply on HN