From brain waves to words: a new path to communication without surgery
107 points
3 hours ago
| 16 comments
| ai.meta.com
| HN
consumer451
27 minutes ago
[-]
Please see my bio for the full rant. The key take-away is:

> While we missed the boat on Internet tracking, there is still time to avoid sailing through the final frontier of neural tracking.

> Thanks to the BCI, we will soon be offered the trade of our privacy for the convenience of password-free login and faster typing. Next, there will be a quick TSA neural scan prior to boarding...

reply
smusamashah
17 minutes ago
[-]
This is the most pessimistic take on this tech here. You can view anything with the same lens.
reply
ImPostingOnHN
6 minutes ago
[-]
Saying "this is the most pessimistic take" doesn't make for good discussion.

Something can have "good takes" but still run an unacceptable risk of ending badly

reply
Junk_Collector
3 hours ago
[-]
It's worth noting that this isn't new technology. This paper is specifically about how their new technique provides a small but statistically significant improvement on existing techniques.

The fact that they provide code and dataset is really praiseworthy.

reply
bpiche
1 hour ago
[-]
I still think of this video often and wonder if it is building on any of that technology, almost 10 years old now. Just looking at this whitepaper it seems like they both use some kind of infrared transcranial light, but never imagined the machine in the original iteration was so big [Regina Dugan's Keynote at Facebook F8 2017 | Inverse] https://www.youtube.com/watch?v=kCDWKdmwhUI
reply
alexpotato
3 hours ago
[-]
So attended an interesting talk a couple years ago:

- fMRI and/or brain implants are the best to figure out brain waves

- but they are expensive or invasive

- EEG is a lot cheaper and easier but not as precise

- BUT what if you used LLMs to analyze EEG data taken at the same time as brain implants etc

The answer seemed to be that "yes, you can get better than traditional EEG data using EEG + LLMs". Curious to see where this ends up and hopefully not that like that Black Mirror episode with the brain scanning leading to murders.

reply
devindotcom
3 hours ago
[-]
reply
albemuth
46 minutes ago
[-]
One practical application comes to mind: [China’s Robot Juggernaut Unitree Debuts a $650,000 Personal Gundam ](https://gizmodo.com/chinas-robot-juggernaut-unitree-debuts-a...)
reply
egypturnash
2 hours ago
[-]
I do not trust Zuckerberg anywhere near my brain waves.
reply
Gigachad
1 hour ago
[-]
Imagine the shareholder value if he could just beam ads directly in to your brain.
reply
johnsmith1840
1 hour ago
[-]
Lightspeed briefs, for the discriminating crotch!
reply
t_gamer_kle
2 hours ago
[-]
And you reverse it to go from words to brain waves! Mind reading at a distance.
reply
dclavijo
2 hours ago
[-]
great news!, I would like to conversate with my dog...i'm sure he has more important thing than lots of people
reply
voxelghost
1 hour ago
[-]
Now, your dogs may very well be smarter than mine. But here's how I imagine a convo with my dogs would go.

- Let's go see what's on the other side of this door, friend, maybe there's food !!

Ok, friend, here you go. - opens door.

- Wow super cool, now let's go see what's on the other side of this door, friend, maybe there's food !!

reply
ksd482
2 hours ago
[-]
If one were to go about translating brain waves from dogs to meaning, we'd run into a big problem immediately: vocabulary resolution.

What I mean by that is we'll have a very limited number of words to which a dog's brainwaves can be translated to since we aren't able to understand them beyond their basic instincts of food, survival, fear, affection towards their owner etc.

There is just no way to go past what we have already observed by their behavior since dogs can't talk or write.

I do wonder how animals think. Perhaps this resolution would also be the theoretical maximum?

reply
supern0va
2 hours ago
[-]
>There is just no way to go past what we have already observed by their behavior since dogs can't talk or write.

There are many dogs that have been trained to press buttons corresponding to words, in the extreme case tens/hundreds of buttons/words, and they can even construct rudimentary sentences. It doesn't seem insane to me that we could perhaps do a very rudimentary version of this for dogs, given a large enough training set.

reply
gloyoyo
1 hour ago
[-]
Some important ones like, "earthquake", "Seizure", etc...

Might be of use.

reply
yieldcrv
1 hour ago
[-]
but that's imposing our language on them, when we should be understanding them

there's a movie about that default human hubris, it spoils it though

reply
righthand
1 hour ago
[-]
Does your dog want to converse with you or anyone?
reply
Havoc
1 hour ago
[-]
Reminds me of the scene in series Incorporated where a megacorp uses this sort of tech to interrogate an employee from a competitor mega-corp to get at a trade secret.

It's a little spooky how real that could now be. Oh and that series was a dystopian series because ofc it was

reply
androiddrew
1 hour ago
[-]
Zuck won't stop even after he knows what you are thinking
reply
mpenick
3 hours ago
[-]
Now the remaining problem is to make Magnetoencephalography devices affordable and not insanely huge.
reply
traverseda
3 hours ago
[-]
From a few days ago, uses ultrasound.

https://news.ycombinator.com/item?id=48685558

reply
greentea23
2 hours ago
[-]
The ultrasound technique there is more like MRI, static imaging, not measuring dynamic electrical signals. Also, regardless of static vs moving, all of this hinges on massive relatively expensive devices (ultrasound is never going to be dirt cheap or miniaturized compared to a smartwatch or even a VR headset) and for the subject to remain perfectly still and probably go through regular calibration sequences. All for <75% accuracy on simple classification tasks. The information mixes in the propagation out of the skull, erasing information. It's analogous to trying to do a row hammer attack on a CPU from outside the computer case.

Also, in the Meta result here, "while actively typing" is actually quite different than passive mind reading because the motor cortex sits nicely near the top surface of the skull, and the muscle memory from past typing makes for a nice well formed signal to measure and classify. It's the same trick over and over since the Brown BrainGate days where you can have people perform or imagine movements and get a decent but not good classification result, and it never gets much better after that trick is exploited. Project dies, VCs and grant writers forget or never appreciated the effect, time goes by, a grad student or corporate research lackey rediscovers it, media puts out an article claiming mind reading is here, and the cycle repeats...

reply
hackermeows
3 hours ago
[-]
why is there no live demo? Anyone seen this in action? Can someone share a demo video or something
reply
ge96
3 hours ago
[-]
The size of that machine
reply
lwhi
3 hours ago
[-]
The participants end up looking a bit like Toad from Mariokart.

How realistic would it be to make a smaller device?

reply
jeffbee
2 hours ago
[-]
Patients should get a "My other hat is a superconducting quantum interferometer" hat.
reply
GaggiX
3 hours ago
[-]
Someone should try it while sleeping and see if anything is related to a dream.
reply
iwassayinbourns
2 hours ago
[-]
This wouldn’t work. Apart from it being very difficult to get people to sleep deeply enough for them to dream in machines like this, the brain state is very different whilst asleep compared with awake. Also the data generated from typing would be very different than thought since it’s likely picking up on broad electrical activity in the primary motor cortex.

Source: spouse works in a sleep lab studying dreams with MRI

reply
ASTP001
2 hours ago
[-]
what sleep lab does your spouse work at? i'm curious about studying dreams
reply
dang
2 hours ago
[-]
[stub for offtopicness]

p.s. come on you guys - this is not what HN is for. You may not owe $megacorp better but you owe this community better if you're participating here.

reply
999900000999
3 hours ago
[-]
Feels like the premise for a spy comedy with a protagonist whose mind can’t be read.

When the bad guys try they just get the lyrics to Yoko Ono music.

reply
moolcool
3 hours ago
[-]
It'll be a cold day in hell before Meta gets access to my brainwaves. Good heavens, can you imagine?
reply
kibwen
3 hours ago
[-]
I'm glad that, with any luck, I'll be dead before this kind of thing is commonplace.
reply
vlian2088
1 hour ago
[-]
2034: brainwave readers are now production-ready

2035: every phone comes with one so you can can do things without clicking any yucky buttons

2036: China mandates phone manufacturers to capture and submit brain data to the state to protect the children and promote social harmony. EU and US condemn. the media condemns.

2037: the EU mandates phone manufacturers to capture and submit brain data to the state to protect the children and fight malinformation. the media applauds.

2038: the US, ruled by the blue party, mandates phone manufacturers to capture and submit brain data to the state to protect the children and combat white nationalism. the red party condemns.

2039: the US, now ruled by the red party, abolishes the previous law and introduces a new one, mandating phone manufacturers to capture and submit brain data to the state to protect the children and combat illegal immigration. the blue party condemns.

reply
fooker
2 hours ago
[-]
@dang How is this offtopic?

Meta has shown remarkable disregard to users' and employees' privacy.

Why should that not come up when discussing an entirely new dystopian technology that allows them to invade privacy at scale?

reply
tantalor
3 hours ago
[-]
Do they test against people not in their training cohort?
reply
setnone
3 hours ago
[-]
non-invasive tech from meta? i don't buy that
reply
botfriendsarent
3 hours ago
[-]
I tried it all it said was "Hot or not?" before it crashed
reply
TheOtherHobbes
3 hours ago
[-]
A word recondition ration of 78% is still petty poop.
reply
dang
2 hours ago
[-]
"Please don't post shallow dismissals, especially of other people's work. A good critical comment teaches us something."

https://news.ycombinator.com/newsguidelines.html

reply
NiloCK
3 hours ago
[-]
Any minute: wear it permanently to sell training data on LLMs. Take an audited IQ test to negotiate your rate.

Better than text-stripping the internet - this thing will soon be pulling the logits as well.

reply
dang
2 hours ago
[-]
"Please don't post shallow dismissals, especially of other people's work. A good critical comment teaches us something."

"Don't be snarky."

https://news.ycombinator.com/newsguidelines.html

reply
NiloCK
2 hours ago
[-]
Great respect to site guidelines, and to you. Object on both counts.

1. The post was obviously bullish / optimistic on the technical capabilities. Not in the least dismissive.

2. The economics extrapolation is obvious. See current precedent for paid access for purchased screen-casts of dev work: https://pdoom.org/open_calls/04_crowd_cast.html

reply
UltraSane
3 hours ago
[-]
I can actually see this happening someday. Theoretical physicists could charge thousands of dollars an hour.
reply
throwawalien
3 hours ago
[-]
if you think they're going to pay people for their data you haven't been paying attention

they'll just put it buried on page 450 of the meta glasses 3 or something

reply
UltraSane
2 hours ago
[-]
They are already paying scarce labor like medical doctors and lawyers hundreds of dollars an hour to create training data. The RoI for training data is high because it can be used to train many models.
reply
fooker
3 hours ago
[-]
Coming soon to a Meta office near you: brain-scanning to make sure employees are focused, happy, and productive!

There are no layoffs in Ba Sing Se.

reply
celeries
2 hours ago
[-]
If this happens, I'll be listening to music with the most annoying lyrics on repeat.
reply
1970-01-01
3 hours ago
[-]
The dystopian future will use this to get passwords/passphrases.
reply
LPisGood
3 hours ago
[-]
Wouldn’t a wrench work just as well?
reply
1970-01-01
2 hours ago
[-]
No, the wrench only works as a threat. Once you beat the brains out of someone, you can't try again.
reply
sublinear
3 hours ago
[-]
It's much easier to resist torture.
reply
iLoveOncall
3 hours ago
[-]
The future is dark.
reply
whimsicalism
3 hours ago
[-]
Interesting -- really excited for the future of human-brain interfaces and just in general more interface exploration enabled by large transformers. I'm already very excited by voice, although wish I could get something akin to the subvoc common in scifi novels. Seems like it would be an easier path than human-brain and would allow me to use voice models in public.

As an aside, disappointed by the very low quality of comments on this article here.

reply