BrainGPT turns thoughts into text

I did a PhD in brain-computer interfaces, including EEG and implanted electrodes. BCI research to a big extent focuses on helping paralyzed individuals regain communication.<p>Unfortunately, EEG doesn’t provide sufficient signal-to-noise ratio to support good communication speeds outside of the lab with Faraday cages and days&#x2F;weeks of de-noising including removing eye-movement artifacts in the recordings. This is a physical limit due to attenuation of brain’s electrical fields outside of the skull, which is hard to overcome. For example, all commercial “mind-reading” toys are actually working based off head and eye muscle signals.<p>Implanted electrodes provide better signal but are many iterations away from becoming viable commercially. Signal degrades over months as the brain builds scar tissue around electrodes and the brain surgery is obviously pretty dangerous. Iteration cycles are very slow because of the need for government approval for testing in humans (for a good reason).<p>If I wanted to help a paralyzed friend, who could only move his&#x2F;her eyes, I would definitely focus on the eye-tracking tech. It hands-down beat all BCIs I’ve heard of.

Ground Truth: Bob attended the University of Texas at Austin where he graduated, Phi Beta Kappa with a Bachelor’s degree in Latin American Studies in 1973, taking only two and a half years to complete his work, and obtaining generally excel- lent grades.<p>Predict: was the University of California at Austin in where he studied in Beta Kappa in a degree of degree in history American Studies in 1975. and a one classes a half years to complete the degree. and was a excellent grades.<p>Wow. That seems comparable to the rudimentary _voice_ to text systems of the 70s and 80s. The brain interface is quickly leaving the realm of sci-fi and becoming a reality. I’m still not sure how I feel about it.

&gt; While it’s not the first technology to be able to translate brain signals into language, it’s the only one so far to require neither brain implants nor access to a full-on MRI machine.<p>I wonder whether, in a decade or two, if the sensor technology has gotten good enough that they don&#x27;t even need you to wear a cap, just there&#x27;ll be people saying &quot;obviously you don&#x27;t have any reasonable expectation of not having your thoughts read in a public space, don&#x27;t be ridiculous&quot;. What I mean is, we just tend to normalize surveillance technology, and I wonder if there&#x27;s any practical limit to how far that can go.

Everyone is this thread immediately went to mind readers as interrogation. But what about introspection? Many forms of teaching and therapy exist because we are incapable of self analyzing in a completely objective way.<p>Being able to analyze your thought patterns outside your own head could lead to all sorts of improvements. You could find which teaching techniques are actually the most effective. You could objectively find when you are most and least focused. You could pinpoint when anxious thoughts began and their trigger. And best of all, you could do this personally, with a partner, or in a group based on your choice.<p>Also you can give someone an FMRI as a brain scanning polygraph today. But there are still a ton of questions about it’s legitimacy.<p><a href="https:&#x2F;&#x2F;scholarship.law.columbia.edu&#x2F;cgi&#x2F;viewcontent.cgi?article=3016&amp;context=faculty_scholarship" rel="nofollow noreferrer">https:&#x2F;&#x2F;scholarship.law.columbia.edu&#x2F;cgi&#x2F;viewcontent.cgi?art...</a>

Reminds me of DARPA &quot;Silent Talk&quot; from 14 years ago. The objective was to &quot;allow user-to-user communication on the battlefield without the use of vocalized speech through analysis of neural signals&quot;<p><a href="https:&#x2F;&#x2F;www.engadget.com&#x2F;2009-05-14-darpa-working-on-silent-talk-telepathic-communication-for-sold.html?guccounter=1&amp;guce_referrer=aHR0cHM6Ly93d3cuZ29vZ2xlLmNvbS8&amp;guce_referrer_sig=AQAAAEQ550sP5_R3bDOO9AkXnQjDLUEuh3lFC6zQjhsEXowYSBJkryIYZep177OXI5ErJqlXjMMZvEpJQU-dhoLvnnV7GrSAL8PbKd0_pL6gPABYEZEiCLd85bsRsq8rhLCLW6SJ2NbPx9y9RHfuXxuOHjuXY0DR2rYHM506af6sOi8H" rel="nofollow noreferrer">https:&#x2F;&#x2F;www.engadget.com&#x2F;2009-05-14-darpa-working-on-silent-...</a>

This is very impressive and useful, and horrifying all at once.<p>I imagine it would help a stroke patient, I also imagine it would give out unfiltered thoughts, which might be troublesome.

Maybe I&#x27;m missing something huge here but a blind controlled demo where the subject committed words to paper and then compared the results afterwards would be persuasive. Unfortunately, the demo as presented in the article seemed achievable by professional magicians and mentalists.<p>I&#x27;m sure we&#x27;re close to brain interfaces, but something seems off about this one.<p>Let&#x27;s say a couple years from now, someone invents an airport scanner that &quot;detects&quot; evil thoughts, except there is no way to verify it, and no accountability for false negatives. The result is whatever the operator says it is. If enough people accept it enough to not resist it, and even turn on the ones who are detected by it, it doesn&#x27;t matter what&#x27;s real because it&#x27;s just a participatory ritual of sympathetic magic. I feel like there are examples of similar dynamics in recent memory.

I wonder if a-linguistic thought could work too. Maybe figure out what your dog is thinking or dreaming about, based on a dataset of signals associated with their everyday activities.<p>It seems like outputting a representation of embodied experience would be a difficult challenge to get right and interpret, though perhaps a dataset of signals associated with embodied experiences could more readily be robustly annotated with linguistic descriptions using a vision-to-language model, so that the canine mind reader could predict and output those linguistic descriptions instead.<p>Imagine knowing the specific park your dog wants to go to, or the subtle early signs of an illness or injury they&#x27;re noticing, or what treat your dog wants you to buy.

FYI The base model that this one uses had some bug in their code which had inflated their baseline results. They are investigating the issues - <a href="https:&#x2F;&#x2F;github.com&#x2F;duanyiqun&#x2F;DeWave&#x2F;issues&#x2F;1">https:&#x2F;&#x2F;github.com&#x2F;duanyiqun&#x2F;DeWave&#x2F;issues&#x2F;1</a>

Aside from all the horrific implications, this enables something very cool: two-way telepathic communication.<p>Think your message, think &quot;send&quot;, hear responses via earbud. With voice cloning, you even get the message in the sender&#x27;s voice. Totally silent and invisible to outside observers.

It’s crazy to me that someone has developed a technology that literally reads peoples mind fairly accurately and its just like a semi popular post on Hacker News.

now&#x27;s a good time to get into meditation, lest you want the advertisers to read your unfiltered thoughts!

Using EEG to predict thought is like looking at the clouds in Mumbai to predict the clouds in Austin. The electrical signal from individual neurons are lost in a sea of large-scale oscillations, which are further blurred by the layers of bone, muscle, and tissue that separate the device from the brain. Bitrate is like 1 bit per second, completely insufficient for most use-cases.

<p><pre><code> And if my thought-dreams could be seen They’d probably put my head in a guillotine But it’s alright, Ma, it’s life, and life only</code></pre>

With half of individuals reportedly having no internal monologue, would this be useless with them? Or just render unintelligible results?

I&#x27;m a bit confused by the eavesdropping on thoughts conclusions being drawn. Did I misinterpret something, or wouldn&#x27;t this be (currently) quite limited for &quot;mind-reading&quot; if it only picks up signals from reading and learns them. There is a difference between mapping &quot;inner voice&quot; and whatever is read.<p>Granted there may be chains of assumptions of advancement involved between them into actual thought-reading, but we&#x27;ve seen before how the devil has hid in those details in advancement chains. See all of the problems with autonomous vehicles in practice. People kind of suck at predicting what problems will be easy to solve.

<a href="https:&#x2F;&#x2F;youtu.be&#x2F;crJst7Yfzj4" rel="nofollow noreferrer">https:&#x2F;&#x2F;youtu.be&#x2F;crJst7Yfzj4</a><p>Not sure on the accuracy in these examples, but this video may be showing the words&#x2F;min speed of the system.

Can we train an LLM based on brainwaves rather than written text? Seems to be closer to how we actually think and thus should enable the LLM to learn to think rather than just learn to mimic the output.<p>For example, when writing we have often gone done many thought paths, evaluated each and backtracked etc, but none of that is left in the text an LLM trains on today. Recording brainwaves and training on that is probably the best training data we could get for LLMs.<p>Getting that data wouldn&#x27;t be much harder than paying humans to solve problems with these hats on recording their brainwaves.

A lie detector?<p>If it can extract words from my grey spaghetti then maybe it can extract my intention too.<p>That&#x27;s probably incredibly obvious and I&#x27;m silly for even bringing it up.

It might be far more effective to capture subvocalisations using surface electrodes and then running those signals through machine learning: <a href="https:&#x2F;&#x2F;annals-csis.org&#x2F;Volume_11&#x2F;drp&#x2F;pdf&#x2F;153.pdf" rel="nofollow noreferrer">https:&#x2F;&#x2F;annals-csis.org&#x2F;Volume_11&#x2F;drp&#x2F;pdf&#x2F;153.pdf</a>

Now...1984 REALLY begins...

This is from a paper published back in September btw: <a href="https:&#x2F;&#x2F;arxiv.org&#x2F;pdf&#x2F;2309.14030.pdf" rel="nofollow noreferrer">https:&#x2F;&#x2F;arxiv.org&#x2F;pdf&#x2F;2309.14030.pdf</a>

Similar work for turning thoughts into images: <a href="https:&#x2F;&#x2F;medarc-ai.github.io&#x2F;mindeye&#x2F;" rel="nofollow noreferrer">https:&#x2F;&#x2F;medarc-ai.github.io&#x2F;mindeye&#x2F;</a>

Seems like it could just be getting at some phonetic encoding, or even raw audio information. The grammatical and vocab transformations could be accounted for by an imperfect decoder.

The article or the video didn&#x27;t explicitly say how many words &#x2F; min they were doing. If the video was not just a demo (like Google) then its very impressive on speed alone.

I’ve been wondering lately about the role of language in the mind and if we might in the future develop a successor that optimizes for how our brains work.

How long from reading thoughts to writing thoughts?

Can it read passwords?<p>I&#x27;m guessing it would be worse at reading passwords like &quot;784&amp;Ghkkr!e&quot; than &quot;horse staple battery ...&quot;

pretty interesting but with how much current llms get wrong or hallucinate i’d be pretty wary of trusting the output, at least currently.<p>amazing to think of where this could be in 10 or 20 years.

I bet this will make Neuralink useless! It would be great for the poor animals getting operated!

Must be great for interrogation.

Sword Art Online when?

Why not link to the paper instead of this shitty website? <a href="https:&#x2F;&#x2F;arxiv.org&#x2F;abs&#x2F;2309.14030v2" rel="nofollow noreferrer">https:&#x2F;&#x2F;arxiv.org&#x2F;abs&#x2F;2309.14030v2</a>

&quot;Seriously, what were these researchers thinking? This &#x27;BrainGPT&#x27; thing is a disaster waiting to happen. Ching-Ten Lin and his team of potential civilization destroyers at the University of Technology Sydney might be patting themselves on the back for this, but did they stop to think about the real-world implications? We&#x27;re talking about reading thoughts—this isn&#x27;t sci-fi, it&#x27;s real, and it&#x27;s terrifying. Where&#x27;s the line? Today it&#x27;s translating thoughts for communication, tomorrow it could be involuntary mind-reading. This could end privacy as we know it. We need to slam the brakes on this, and fast. It&#x27;s not just irresponsible; it&#x27;s playing with fire, and we&#x27;re all at risk of getting burned.<p>Like, accurate brain readers are right under DWIM guns in the pantheon of things thou mustn&#x27;t build!