a couple hours ago i had astra take on a 10 month old repo of mine https://github.com/callbacked/neural-band-poc/ that involved finding a way to use the meta neural band independently from the glasses to read the sEMG data off of it. i really think it is a cool piece of technology that largely gets overlooked by the glasses, and always thought it was a shame it couldn't be used outside of its main application.
after making quick work of that, i wanted to use it to control my mac using gesture controls and that's how kinesis was born. it has been very cool being able to swipe from desktops using my fingers, swiping up to open up mission control or controlling a virtual knob to adjust my volume.
i definitely havent scratched the surface with the neural band but it has been a really fun endeavor thus far! i really hope others can find creative uses for their neural bands too :)
note: i really hope this works on other bands because the sample size has just been me so far.
Discoverability is the degree to which something, especially a piece of content or information, can be found in a search of a file, database, or other information system. Discoverability is a concern in library and information science, many aspects of digital media, software and web development, and in marketing, since products and services cannot be used if people cannot find it or do not understand what it can be used for.
Most search engines support the use of the Boolean operators AND, OR and NOT to help end users refine the search query. Boolean operators are for literal searches that allow the user to refine and extend the terms of the search
Not sure about you, but if I'm trying to find a tool, I don't search just "Houdini", but I'm also an adult who can put two terms together. I linked the above page in hopes that it might help you more efficiently use search engines in the future just like me.
Do you think it's likely someone goes looking for the real-time data processing platform, lands on this GitHub and gets confused?
No, but I do think it is likely that someone might find this while looking for the kinesis keyboard, a popular product which has been on the market for 34 years.
Walking around wearing Meta’s hardware supports them by you advertising their product (unless you never show anyone that you own the hardware).
The existence of a used market also slightly increases the value of new things. By buying used, you’re supporting/signaling the used market and indirectly supporting the company.
If you don’t want to support a company, don’t go near their products.
“Advertising the product” is an extremely mild form of support in this case.
Your criticism of buying used is complete nonsense. Secondary markets have put companies out of business. You’re not “signaling” anything except that the price is too high.
You are right, it's double-edged. In some cases it can hurt companies (e.g. luxury good companies) while in other cases it can benefit them (e.g. car companies benefit from the second-hand market in many ways). It's a fascinating economics+psychology topic.
I'd have to be pretty sure I could use the hardware forever without a login for me to let it near my systems. Anything with firmware or a security footprint would not qualify.
I might accept a Meta paperclip into my house, but then again, why risk it ;)
Meta's game is to do all sorts of dirty tricks to pull you into its data. No thanks.
The neural band always looked more interesting than the glasses tbh.
I've been moving more and more away from terminal and IDEs, and I've been exploring how I could move to a flip phone / table + compact keyboard as most of my development time is now possible to be done via just using TTS.
I'd be interested in exploring if something like this could remove the need for a mouse or touching the screen as well.
Some alternatives that are not bound to the meta glasses: Mudra Link (USD 299), Mudra Band for Apple Watch (USD 350), MindRove Armband (USD 800, wow), SiFi Labs SiFi Band (no price), OYMotion gForce Pro+ (USD 1250, ok this side project is starting to look expensive)
Yep, and IMHO that's why eye tracking even though is amazing when it does work is still very limited. We do a lot of small things without even realizing and stopping to do movements we are not aware of is very very hard.
I think the inertia of familiar input devices is way too high for something like that to gain any sort of traction. For better or for worse, the mainstream user is probably not leaving his QWERTY keyboard and his touchscreen, even in use cases where those are highly suboptimal.
Keyboards are wildly suboptimal. Inertia is only an issue when you replace suboptimal with only slightly better suboptimal. The transition period from blackberry (keyboard-based phones) to iphones did not take long at all (relatively speaking of course).
suboptimal for which tasks and what's better then?
I spend a LOT of time with different interfaces
(eye tracking, 6DoF controllers, pens, touchpad in keyboard, ergonomic mouse, etc) and... basically if there is 1 thing I'm confident about is that input methods are very task dependent. If you want to input text, especially hard to pronounce keywords and symbols, keyboard is great, if you want to move a pointer at arbitrary position in 3D keyboard sucks. It also depends on the context, behind a desk vs on the move is totally different.
IMHO inertia isn't the biggest factor, training requirement is.
I switched recently from mouse to touchpad and ... next day my great ergonomic mouse was basically in a drawer. Meanwhile when I tried to use Tap Strap the first step was to learn combinations with basically no gradient of feedback, it was either success or failure.
Inertia isn't such a big problem if the investment is small but if you have to learn an entirely new way then it's a huge risk.
Very interesting. So how open is the neural band to hack on? Do you expect this to be something to get patched out eventually if you update? Seems like a really cool platform to develop against outside of the intended ecosystem.
You can do that without bands since 2019 with the Meta Quest. Hand tracking and (for that old one only black & white) video pass through is enough, no need to additional hardware.
This looks like it could potentially be a huge productivity win. The ergonomics seem tantalizingly similar to the infamous scene from Minority Report where Tom Cruise manipulates translucent data streams with his bare hands.
Could I suggest that you shoot a new promotional demo video with enough lighting that viewers can see your hands? Personally I'd be very curious to see and understand the actual gestures that support a real world workflow involving multiple desktops and applications, with the hands transitioning as needed between neural band mode for navigation vs. keyboard/mouse mode for fine-grained motor inputs.
In another prototype—again, heavy on the use of what he called "materials that move at the speed of thought," such as coat hangers, tape, fishing line, projectors, chopsticks, and a presentation clicker—they learned that the Minority Report style of interfacing with a computer by swiping with your hands at images was actually a poor idea. While people loved trying out the prototype, even the strongest found that their arms and shoulders soon began to hurt.
Agreed but tbh it's not fair, nobody is even typing 8hrs/day.
FWIW it's very to test by the way, pick a random XR demo support hand tracking and you will see it's not that tiring. It doesn't mean it's useful though.
I've heard from several people who've tried the KiWear ring that the experience is close to using the neural band. Different form factor and technology though.
You can bind a hand position or gesture (e.g. going from one position to another) to a desktop command by running this in the background on your NodeJS companion app and spawn() for the commands.
after making quick work of that, i wanted to use it to control my mac using gesture controls and that's how kinesis was born. it has been very cool being able to swipe from desktops using my fingers, swiping up to open up mission control or controlling a virtual knob to adjust my volume.
i definitely havent scratched the surface with the neural band but it has been a really fun endeavor thus far! i really hope others can find creative uses for their neural bands too :)
note: i really hope this works on other bands because the sample size has just been me so far.
Meta doesn’t sell these separately from the glasses :(
Are they patented to heck and back or can another manufacturer make a EMG bracelet for controlling a PC?
Not sure how well it works but that is supposed to do the same thing
https://mudra-band.com/products/mudra-link
https://www.tindie.com/products/waveletech/18-channel-emg-sm...
Kinesis is already a word and an Amazon product, might have better discoverability naming your project something unique and specific.
And a band, and a company, and a .... https://en.wikipedia.org/wiki/Kinesis
Do you think it's likely someone goes looking for the real-time data processing platform, lands on this GitHub and gets confused?
Discoverability is the degree to which something, especially a piece of content or information, can be found in a search of a file, database, or other information system. Discoverability is a concern in library and information science, many aspects of digital media, software and web development, and in marketing, since products and services cannot be used if people cannot find it or do not understand what it can be used for.
https://en.wikipedia.org/wiki/Discoverability
https://en.wikipedia.org/wiki/Search_engine
Not sure about you, but if I'm trying to find a tool, I don't search just "Houdini", but I'm also an adult who can put two terms together. I linked the above page in hopes that it might help you more efficiently use search engines in the future just like me.
Search engines are so 2010. You just announce "hey genie!" and ask for what you want.
No, but I do think it is likely that someone might find this while looking for the kinesis keyboard, a popular product which has been on the market for 34 years.
Amazon was already a word.
Facebook was already a word.
Meta was already a word.
You're right. They would have been much more successful if they had chosen "something unique and specific".
I don't think anybody would take a flight to Brazil to see an Amazon shop and vice versa.
In this specific case though as others pointed out there are already a lot of products on that specific segment with that name.
omg..I hate FB and I actually want that..
Definitely interesting work, but Meta will get nothing from me, as far as I can help it.
No level of convenience will tip that scale.
Meta doesn’t make money if you buy its hardware used on eBay or similar
Walking around wearing Meta’s hardware supports them by you advertising their product (unless you never show anyone that you own the hardware).
The existence of a used market also slightly increases the value of new things. By buying used, you’re supporting/signaling the used market and indirectly supporting the company.
If you don’t want to support a company, don’t go near their products.
“Advertising the product” is an extremely mild form of support in this case.
Your criticism of buying used is complete nonsense. Secondary markets have put companies out of business. You’re not “signaling” anything except that the price is too high.
You are right, it's double-edged. In some cases it can hurt companies (e.g. luxury good companies) while in other cases it can benefit them (e.g. car companies benefit from the second-hand market in many ways). It's a fascinating economics+psychology topic.
I'd have to be pretty sure I could use the hardware forever without a login for me to let it near my systems. Anything with firmware or a security footprint would not qualify.
I might accept a Meta paperclip into my house, but then again, why risk it ;)
Meta's game is to do all sorts of dirty tricks to pull you into its data. No thanks.
The neural band always looked more interesting than the glasses tbh.
I've been moving more and more away from terminal and IDEs, and I've been exploring how I could move to a flip phone / table + compact keyboard as most of my development time is now possible to be done via just using TTS.
I'd be interested in exploring if something like this could remove the need for a mouse or touching the screen as well.
Some alternatives that are not bound to the meta glasses: Mudra Link (USD 299), Mudra Band for Apple Watch (USD 350), MindRove Armband (USD 800, wow), SiFi Labs SiFi Band (no price), OYMotion gForce Pro+ (USD 1250, ok this side project is starting to look expensive)
The neural band could become a standard interface for situations where keyboards and mice are not practical.
Does it really have enough fidelity of distinguishing gestures for that today?
I was under the impression the set is pretty limited and maybe not completely robust (like per person setup/calibration etc.)
I'm always worried about the "Midas effect" with something like that. Having to be careful not to trigger actions you don't want to.
Yep, and IMHO that's why eye tracking even though is amazing when it does work is still very limited. We do a lot of small things without even realizing and stopping to do movements we are not aware of is very very hard.
I think the inertia of familiar input devices is way too high for something like that to gain any sort of traction. For better or for worse, the mainstream user is probably not leaving his QWERTY keyboard and his touchscreen, even in use cases where those are highly suboptimal.
Keyboards are wildly suboptimal. Inertia is only an issue when you replace suboptimal with only slightly better suboptimal. The transition period from blackberry (keyboard-based phones) to iphones did not take long at all (relatively speaking of course).
suboptimal for which tasks and what's better then?
I spend a LOT of time with different interfaces (eye tracking, 6DoF controllers, pens, touchpad in keyboard, ergonomic mouse, etc) and... basically if there is 1 thing I'm confident about is that input methods are very task dependent. If you want to input text, especially hard to pronounce keywords and symbols, keyboard is great, if you want to move a pointer at arbitrary position in 3D keyboard sucks. It also depends on the context, behind a desk vs on the move is totally different.
So yes quite curious about such a wide statement.
IMHO inertia isn't the biggest factor, training requirement is.
I switched recently from mouse to touchpad and ... next day my great ergonomic mouse was basically in a drawer. Meanwhile when I tried to use Tap Strap the first step was to learn combinations with basically no gradient of feedback, it was either success or failure.
Inertia isn't such a big problem if the investment is small but if you have to learn an entirely new way then it's a huge risk.
Consider also Tap Band then.
I worked a bit with Tap Strap on XR and without but in my experience once you master a keyboard nothing comes close while manipulating text, e.g code.
https://tapwithus.com this looks interesting indeed, thank you!
I seem to have completely missed the Neural Band as this is my first time even seeing it, but I have to admit - it does look quite cool.
Anyone have any long-term hands-on experience with it? Would love to know if it feels clunky or not...
The vibe coders have finally discovered their killer interface, and it is kind of cool, especially if integrated with voice inputs.
that seems so cool lol
Very interesting. So how open is the neural band to hack on? Do you expect this to be something to get patched out eventually if you update? Seems like a really cool platform to develop against outside of the intended ecosystem.
I want to wear 2 of these bands and have multi touch AR. In thinking like pinch to zoom for reality.
You can do that without bands since 2019 with the Meta Quest. Hand tracking and (for that old one only black & white) video pass through is enough, no need to additional hardware.
Cool! I had no idea
I have an old Leap motion sitting around.. I'd imagine I might be able to do something similar with it?
This looks like it could potentially be a huge productivity win. The ergonomics seem tantalizingly similar to the infamous scene from Minority Report where Tom Cruise manipulates translucent data streams with his bare hands.
Could I suggest that you shoot a new promotional demo video with enough lighting that viewers can see your hands? Personally I'd be very curious to see and understand the actual gestures that support a real world workflow involving multiple desktops and applications, with the hands transitioning as needed between neural band mode for navigation vs. keyboard/mouse mode for fine-grained motor inputs.
That scene in Minority Report looked cool but how tiring would it be to have your hands suspended in the air for 8 hours a day?
https://www.mitre.org/news-insights/impact-story/rapid-proto...
Agreed but tbh it's not fair, nobody is even typing 8hrs/day.
FWIW it's very to test by the way, pick a random XR demo support hand tracking and you will see it's not that tiring. It doesn't mean it's useful though.
Feels like such a misnomer, but I guess that's marketing.
I remember when OCZ NIA came out and it claimed BCI and it was effectively doing muscle activity too.
At least meta is properly representing what it does!
Kinesis is a legendary keyboard brand.
I've heard from several people who've tried the KiWear ring that the experience is close to using the neural band. Different form factor and technology though.
Great to explore alternative interfaces and repurpose existing hardware without having to rely on the manufacturer implementation.
Have you considered providing GadgetBridge support? I don't see anything on https://codeberg.org/Freeyourgadget/Gadgetbridge/issues?stat... but it could bring interesting combinatorial possibilities.
For anybody who wants to try that without any extra hardware but just your webcam give a go to https://codepen.io/mediapipe/pen/bGweWyR based on MediaPipe Hands in JavaScript https://chuoling.github.io/mediapipe/solutions/hands.html
You can bind a hand position or gesture (e.g. going from one position to another) to a desktop command by running this in the background on your NodeJS companion app and spawn() for the commands.
FWIW did something similar using OpenCV https://fabien.benetou.fr/Portfolio/PostureMaintenance 15 years go.
If you also are interested in gaze tracking https://lebmatter.github.io/gazerjs/ is another Web based example.