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

11–20 of 34 posts

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

#11

Post by drdaeman »

rckt wrote: post #9

Why do you need LLM to interpret patterns?

> The researchers ran the audio and motion data through smaller models that generated text captions and class predictions, then fed those outputs into different LLMs (Gemini-2.5-pro and Qwen-32B) to see how well they could identify the activity.

Maybe I'm not understanding it, but as I get it, LLMs weren't really important: all they did was further interpreting outputs of a fronting audio-to-text classifier model.

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

#12

Post by Lerc »

rckt wrote: post #9

Why do you need LLM to interpret patterns?

The same reason you need transistors to make computers.

You don't need them, but they are one way to do it that people know how to implement.

Identifying patterns is fairly amenable to analytic approaches, interpreting them, less so.

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

#14

Post by bigyabai »

macintux wrote: post #8
gizajob wrote: post #6

Time to ditch the Apple Watch then

One more positive interpretation of Apple's research interests here is that devices like the Watch can better differentiate between "the wearer just fell and we should call 911" and "the wearer is playing with their kids".

"Can" does not necessarily mean "will", especially for Apple. I wouldn't be surprised if you're describing a feature slated for release in 2037.

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

#15

Post by b00ty4breakfast »

macintux wrote: post #8
gizajob wrote: post #6

Time to ditch the Apple Watch then

One more positive interpretation of Apple's research interests here is that devices like the Watch can better differentiate between "the wearer just fell and we should call 911" and "the wearer is playing with their kids".

nuclear power generation is pretty beneficial, but that doesn't justify the existence of nuclear weapons.

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

#17

Post by pramsey »

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…

In 1984 the idea was there were not enough people to listen to everyone, all the time, but the mere possibility was enough. Of course, for us with AI, things are considerable worse. Also, tele screens were mandatory. We are not there with cell phones in a de jure sense, but certainly there in a de facto sense. Of course, if enough people carry phones, it doesn't matter if a few stragglers don't, they will get caught in the net unless they live as hermits, in which case who cares about them. All the pieces are in place, there is no reason we cannot have a global North Korea.

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

#18

Post by hexbin010 »

chasing0entropy wrote: post #2

If you're interested in this concept, it's not new and the alarm has been sounded since the android Facebook app required motion sensor permissions in android 4. https://par.nsf.gov/servlets/purl/10028982 https://arxiv.org/pdf/2109.13834.pdf

I tried denying the Sensor perm to most apps and my battery tanked. My guess is there are a few that sit in a busy loop trying to get the data with no handling of the permission not being granted, because it's expected on 99.99999% of devices

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

#19

Post by TZubiri »

The tinfoil interpretatio that LLMs can spy on you is shortsighted and a bit paranoid, it would require LLM providers to actually run a prompt asking what you are doing.

However, any system with a mic, like your cellphone listening for a "Hey Siri" prompt, or your fridge, could theoretically be coupled with an llm on an adhoc basis to get a fuller picture of what's going on.

Pretty cool, if an attacker or govt force with a warrant can get an audio stream they can get some clues although of course not probatory evidence.

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

#20

Post by frizlab »

skavi wrote: post #10

Maybe the 2026 Apple Watch will be able to auto detect running as reliably as my 2015 Samsung Gear S2. My 2022 Series 8 is certainly not there yet.

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).
Post reply on HN