[dead]
Apple Releases Open Weights Video Model
81–90 of 178 posts
Re: Apple Releases Open Weights Video Model
#82The number of video models that are worse than Wan 2.2 and can safely be ignored has increased by 1.
Re: Apple Releases Open Weights Video Model
#83Apple has a video understanding model too. I can't wait to find out what accessibility stuff they'll do with the models. As a blind person, AI has changed my life.
One cool feature they added for deaf parents a few years ago was a notification when it detects a baby crying.
Is that something you actually need AI for though? A device with a sound sensor and something that shines/vibrate a
remote device when it detects sound above some threshold would be cheaper, faster detection, more reliable, easier to maintain, and more.
Re: Apple Releases Open Weights Video Model
#84Earlier quoted context omitted.
As a (web app) developer I never quite sure what to put in alt. Figured you might have some advice here?
One way to frame it is: "how would I describe this image to somebody sat next to me?"
Important to add for blind people: "... assuming they never seen anything and visual metaphors won't work"
The amount of times I've seem captions that wouldn't make sense for people who never been able to see is staggering, I don't think most people realize how visual our typical language usage is.
Re: Apple Releases Open Weights Video Model
#85Earlier quoted context omitted.
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 are one I've wondered about, do I need to try to describe the trend of the data, or provide several conclusions that a person seeing the chart might draw? Just saying "It's a chart" doesn't feel like it'd be useful to someone who can't see the chart. But if the other text on the page talks about the chart, then maybe identifying it as the chart is enough?
What are you trying to point out with your graph in general? Write that basically. Usually graphs are added for some purpose, and assuming it's not purposefully misleading, verbalizing the purpose usually works well.
Re: Apple Releases Open Weights Video Model
#86The number of video models that are worse than Wan 2.2 and can safely be ignored has increased by 1.
To be fair, the sizes aren't comparable, and for the variant that is comparable, the results aren't that much worse.
Re: Apple Releases Open Weights Video Model
#87Earlier quoted context omitted.
One cool feature they added for deaf parents a few years ago was a notification when it detects a baby crying.
Is that something you actually need AI for though? A device with a sound sensor and something that shines/vibrate a remote device when it detects sound above some threshold would be cheaper, faster detection, more reliable, easier to maintain, and more.
>Is that something you actually need AI for though?
Need? Probably not. I bet it helps though (false positives, etc.)
>would be cheaper, faster detection, more reliable, easier to maintain, and more.
Cheaper than the phone I already own? Easier to maintain than the phone that I don't need to do maintenance on?
From a fun hacking perspective, a different sensor & device is cool. But I don't think it's any of the things you mentioned for the majority of people.
Re: Apple Releases Open Weights Video Model
#88Earlier quoted context omitted.
> Something one doesn't see in news headlines. I hope this wasn't a terrible pun
No pun intended but it's indeed an unfortunate choice of words on my part.
My blind friends have gotten used to it and hear/receive it not as a literal “see“ any more. They would not feel offended by your usage.
Re: Apple Releases Open Weights Video Model
#89Earlier 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.
+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...
Re: Apple Releases Open Weights Video Model
#90Earlier quoted context omitted.
One cool feature they added for deaf parents a few years ago was a notification when it detects a baby crying.
Is that something you actually need AI for though? A device with a sound sensor and something that shines/vibrate a remote device when it detects sound above some threshold would be cheaper, faster detection, more reliable, easier to maintain, and more.
But your solution costs money in addition to the phone they already own for other purposes. And multiple things can make loud noises in your environment besides babies; differentiating between a police siren going by outside and your baby crying is useful, especially if the baby slept through the siren.
The same arguments were said for blind people and the multitude of one-off devices that smartphones replaced, OCR to TTS, color detection, object detection in photos/camera feeds, detecting what denomination US bills are, analyzing what's on screen semantically vs what was provided as accessible text (if any was at all), etc. Sure, services for the blind would come by and help arrange outfits for people, and audiobook narrators or braille translator services existed, and standalone devices to detect money denominations were sold, but a phone can just do all of that now for much cheaper.
All of these accessibility AI/ML features run on-device, so the knee-jerk anti-AI crowd's chief complaints are mostly baseless anyways. And for the blind and the deaf, carrying all the potential extra devices with you everywhere is burdensome. The smartphone is a minimal and common social and physical burden.