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

New Apple Study Shows LLMs Can Tell What You're Doing from Audio and Motion Data

9to5mac.com

Post reply on HN
Print view View original

31–34 of 34 posts

Re: New Apple Study Shows LLMs Can Tell What You're Doing from Audio and Motion Data

#31

Post by furyofantares »

mh- wrote: post #22
frizlab wrote: post #20

Earlier quoted context omitted.

That’s weird, I have perfect running detection on an old(er) (Apple) watch. Detection does start late (but is retroactive, so it’s not an issue).

And that's by design, because it waits for a larger window of data to gain confidence. Notice how you ~never get false positives on it starting an exercise session. I see comments like GP's often enough that I think Apple just does a bad job explaining how/why it works.

> Notice how you ~never get false positives on it starting an exercise session.

Oh, I absolutely do.

Re: New Apple Study Shows LLMs Can Tell What You're Doing from Audio and Motion Data

#32

Post by skavi »

mh- wrote: post #22
frizlab wrote: post #20

Earlier quoted context omitted.

That’s weird, I have perfect running detection on an old(er) (Apple) watch. Detection does start late (but is retroactive, so it’s not an issue).

And that's by design, because it waits for a larger window of data to gain confidence. Notice how you ~never get false positives on it starting an exercise session. I see comments like GP's often enough that I think Apple just does a bad job explaining how/why it works.

Personally, I understand perfectly how it works. But even with the retroactive start, it tends to miss the first five or so minutes.

There are also stats on the screen during tracking that ideally should appear as early as possible.

Re: New Apple Study Shows LLMs Can Tell What You're Doing from Audio and Motion Data

#33

Post by palmotea »

godelski wrote: post #7
palmotea wrote: post #4

AI will finally allow us to bring 1984's Telescreens into existence, at scale.

Doesn't the smartphone already far surpass the Telescreen's capabilities and presence? It does more and we carry them in our pockets. Do people not realize we're beyond 1984? In 1984 the tech wasn't always listening, rather it had the capacity to. Much of it was about how not knowing meant you'd act as if you were just in case. It was making reference to totalitarian states where you don't know if you can freely talk…

> Doesn't the smartphone already far surpass the Telescreen's capabilities and presence? It does more and we carry them in our pockets.

Maybe in data collection, but no one's watching.

With AI, someone can always be watching you. It's really the killer app for AI.

Re: New Apple Study Shows LLMs Can Tell What You're Doing from Audio and Motion Data

#34

Post by smcin »

andrewrn wrote: post #3

Something to note here that annoys me about the title is that the LLMs aren't taking in the raw data (LLM's are for text, after all). The raw data is fed through audio and motion models that then produce natural language descriptions, that are then fed to the LLM. Unrelated: yeah, this article is a little creepy, but damn is it interesting technically.

"LLMs" is the new catchall term for Machine Learning or automation, to laypeople. For now.
Post reply on HN