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

Neuralink patient controls games by thinking during interview

twitter.com

Post reply on HN
Print view View original

91–100 of 151 posts

Re: Neuralink patient controls games by thinking during interview

#91

Post by dragonwriter »

Veserv wrote: post #90
brettv2 wrote: post #6

I haven't followed Neuralink too closely since it was announced, so I was not expecting to see what I just saw. I've seen a handful of breakthrough moments in my life - I think this will be remembered as one.

Why would this be remembered as a breakthrough? Playing games with a BCI is many years old at this point. Here is an article from 2020 talking about playing Sonic the Hedgehog, amongst other games [1]. Here he is fist bumping President Obama in 2016 with a brain controlled robot arm. [1] https://www.washingtonpost.com/video-games/2020/12/16/brain-...

Yeah game/simulator control by neural interface is old news (and has been demonstrated with non-invasive interfaces.)

[2015] https://www.smithsonianmag.com/smart-news/paralyzed-woman-op...

[2013] With a non-invasive interface: https://iopscience.iop.org/article/10.1088/1741-2560/10/4/04...

[2011] https://journals.plos.org/plosone/article?id=10.1371/journal...

[2010] https://pubmed.ncbi.nlm.nih.gov/20876032/

Re: Neuralink patient controls games by thinking during interview

#92

Post by dragonwriter »

panick21_ wrote: post #46
zachbee wrote: post #21

From a technical perspective, moving a mouse with your mind isn't entirely new: https://elifesciences.org/articles/18554 Personally, I think the most exciting part of Neuralink and other companies working on BCIs is the fact that they're trying to keep these implants in long-term, and scale the deployment significantly. Most academic BCI research thus far has just been trials, without patients getting to keep the imp…

Moving the mouse wasn't that impressive. That he could turn of the music just like that while the game was open was impressive. And Civ 6 is way more complex to operate compared to chess. I assume that's not mouse driven. Still early days for this tech but it seems impressive.

> And Civ 6 is way more complex to operate compared to chess. I assume that’s not mouse driven.

Civ 6 is drivable completely with the mouse, and other than editing gold amounts in trade offers a little more quickly there’s not much reason to use anything but a mouse for it.

Re: Neuralink patient controls games by thinking during interview

#93

Post by dragonwriter »

axus wrote: post #55
stavros wrote: post #36

Earlier quoted context omitted.

I never could get into Civ. Do you have any tutorials or a specific game edition to recommend? Maybe my issue is that it's too slow to get started with, but it seems like I'd enjoy it if I stuck with it.

The open source clone of 5/6 is pretty fast, games take less time when it's less flashy and more responsive: https://github.com/yairm210/Unciv

Why do you say “5/6”? its an open-source clone of 5, and the Readme notes that given the time it took them to get done with 5 (i.e., not yet, as the base mechanics are only “mostly done” and there’s a bunch of stuff from the expansions still to do), implementing Civ 6 mechanics is an express “won’t-do”.

Re: Neuralink patient controls games by thinking during interview

#94

Post by alexilliamson »

DoesntMatter22 wrote: post #80
ShamelessC wrote: post #69

Earlier quoted context omitted.

That’s fair I suppose but it’s probably giving more credit to Musk than he deserves. The real work is all being done by researchers who are drastically more knowledgeable about all of this than he is. He’s wise to invest in these sorts of ideas though and deserves credit for that.

I think he deserves an awful lot of credit for funding such a pie in th sky idea and giving those researches a chance to even attempt it. In 1 month he's launched the largest rocket ever, done one of the first successful brain implants ever and released a pretty amazing version of FSD. No other billionaires have done even 1 of those things. Even if he was a buffoon he deserves credit foe the audacity.

I was sort of with you until the FSD

Re: Neuralink patient controls games by thinking during interview

#95

Post by Veserv »

ggreer wrote: post #88
dev1ycan wrote: post #85

Earlier quoted context omitted.

I don't think the device itself is a breakthrough, the issue beforehand was that tissue in the brain tries to heal from the implant, it can be lethal, I don't know what they're doing to have a PERMANENT implant, completely stop that area from "healing" so tht the implant doesn't become a legitimate hazard.

The main issues with previous BCIs were that the electrodes were larger, less flexible, and not as biocompatible. This caused scar tissue to form around the electrodes, degrading the quality of the signals and eventually making the device useless. Neuralink has apparently reduced scar tissue formation enough that the implant receives usable signals for years. Neuralink also uses far more electrodes, improving signal…

Can you point to a study showing that Neuralink has achieved any of those things you mentioned? What evidence is there that the implants have reduced scar tissue formation and what supports the assertion that they would be usable for years? What other previous devices are you comparing it to that allows you to positively assert that it is better than them?

You can not just reel off every bullet point on the marketing slides without support as if it is the truth.

Re: Neuralink patient controls games by thinking during interview

#96

Post by Veserv »

elif wrote: post #39
BadHumans wrote: post #11

Earlier quoted context omitted.

They are referring to Tesla promotional FSD videos being heavily edited. https://www.pcmag.com/news/tesla-faked-autopilot-video-engin... While not an Musk company, it is worth remembering Theranos demos being convincingly faked as well. I don't know if it is happening here but it does happen.

That's not faked though.. according to your link they tried multiple times and only showed the success video. But the statement that the software drove with no intervention was accurate, and the video was authentic.

How about that time they claimed the Cybertruck beats a Porsche in a 1/4 mile race, but they only did a 1/8 mile race and then just made up a 1/4 mile time based on their feelings? [1]

Or that time they lied about 120,000 defective suspensions that broke causing crashes and fatalities and then blamed their customers and covered it up so they would not have to issue a recall in the US (they were forced to issue a recall for the issue in China)? [2]

A decade of unequivocal lies about delivering autonomous vehicles [3] while knowingly killing tens to hundreds.

But other than that, Mrs. Lincoln, how was the play?

[1] https://www.youtube.com/watch?v=HRYS5VWXZts

[2] https://www.reuters.com/investigates/special-report/tesla-mu....

[3] https://dawnproject.com/wp-content/uploads/2024/01/Elon-Musk...

Re: Neuralink patient controls games by thinking during interview

#97

Post by Veserv »

panick21_ wrote: post #48
mdeeks wrote: post #43

Earlier quoted context omitted.

FSD being good isn't really the same as the Robotaxi idea. Robotaxi was where you could rent out your car and it could completely autonomously drive other people for a fare. Your car would make money. I haven't seen 12.3 but other versions had some frightening mistakes in videos. It feels like it will eternally be 90% there but never actually reach the end goal of completely autonomy. Personally I love Autopilot even…

I think everybody understand that Musk (and others) were way to aggressive on self driving stuff. What their new version can do is impressive, but as you say, Robotaxi aren't all that close. But do think saying this demo is fake based on to aggressive timelines for self driving is a stretch.

No, they were unequivocal lies. In 2019:“ I think we will be feature-complete full self-driving this year, meaning the car will be able to find you in a parking lot, pick you up, take you all the way to your destination without an intervention — this year. I would say that I am certain of that. That is not a question mark." [1].

See the part where he says: "That is not a question mark." That is called making a clear and direct, unequivocal, unqualified, statement that he knew for certain was wrong. That is called lying.

[1] https://www.businessinsider.com/elon-musk-doubles-down-on-cl...

Re: Neuralink patient controls games by thinking during interview

#98

Post by londons_explore »

I want to know how big the GPU crunching all the numbers is to make this work...

The mouse seems to move very nicely and smoothly (60 FPS?) which presumably means the neural net which converts raw sensor data to mouse movements is running in ~15 milliseconds.

Most neural nets don't do a forward pass in 15ms unless they're either tiny or the GPU is very powerful.

Re: Neuralink patient controls games by thinking during interview

#99

Post by londons_explore »

I'd like to know if they're doing 'online training' - ie. Do the weights of the neural net which converts raw signal data into mouse movements update themselves every few seconds using historical data?

Such online training might be necessary to deal with brain plasticity - ie. The optimal set of neurons to read to determine X/Y mouse movement right now might not be the same set it was an hour ago.

Such plasticity can be seen in regular humans too when they say 'whoa, I haven't used a pen for months - let me get used to writing again!'.

Post reply on HN