My understanding from their original paper is that Synchron’s device (known as the stentrode since its electrodes are on a stent scaffold) decodes only a binary signal for this trial, that is “intent to move” or “no intent to move” in a period of time (~1 second). Their paper mentions the decoder outputting no click, short click, or long click where a short click is movement intent followed by no movement intent, and long click is something like 3 consecutive movement intents followed by no movement intent.

The person types either by using eye tracking to move the cursor and clicking with the BCI device, or with a custom interface that cycles through characters one at a time and using only the BCI device to say yes to that character.

So the decoding of intent isn’t at the level that your thought experiment is concerned about, but in general, you definitely could implement something that decodes an initial intent before subsequent recording (e.g., think about waking up the device). Trivially for Synchron’s device this could be X number of consecutive movement intents. For intracortical BCI devices with single neuron resolution, you could imagine more precise neural activity correlated with the intent to begin decoding.

God I hope someone implements a binary tree for these poor people, I can't imagine how frustrating it must be to type like that.

There is a simpler device, a glass plate with the alphabet held between the patient and the other person. Humans are extraordinary good at following someone's glance, and this is how a quadriplegic patient can spell out words. Franz Rosenzweig used such a thing in his last years.

It's surprising that no one has used a camera plus ML whizzo stuff including predictive text to speed up the process.

Haha, for typical use with Synchron’s device they are using eye-tracking. The BCI-only mode is just for research purposes/baseline. It’s also just what’s in the paper, they may implement other UIs in practice.

> they may implement other UIs in practice

for the first time in my life I'm thinking "now here's something that should be called UX"

Couldn't something pretty close to that be done with eye movement and blinking?

There are a variety of Eye Tracking Communication Devices on the market.

I am not listing the manufacturers since most of them are also involved in either/or/and military and marketing applications and I am done supporting surveillance and murder capitalism.

But the eye movement interfacing tech is there and becoming more and more wide-spread. The major players have pilot studies at hospitals and r&d medical facilities across the world.

With the implant the concept is that with further development, it can be used for connection to locomotion etc. The proposed future potential of direct interfacing is larger, so to say.

An exoskeleton with direct input from a fully paralyzed wearer can significantly contribute to rehab, just one scenario.

This is a really great point.

I feel like I have three levels of thought - unconscious, unprompted and active. Unconscious are what you'd imagine - I don't actively think them (like I don't hear the thought in my head), but clearly something's happening in my brain that's affecting my actions.

Unprompted and active are both things that I hear in my inner monologue or picture in my head. The former, as the name would suggest, are things that I'm not trying to think about - intrusive thoughts are certainly an example. The latter are things that I am purposely shaping my thoughts around.

Active thoughts are almost the only thing that come out of my mouth (if I'm very surprised, an unprompted thought might come out). Would I have that same level of control here?

In past experiments that I'm aware of, you steered the cursor, or typed a letter, by using a few seconds of _visualizing_ a sort of "command image". The command image recall would essentially generate a recognizable signal in a sensor array that is in a cap the patient wears.

When I'm trying to be funny, I'll sometimes feel a funny joke coming, but I have no idea what it'll be. Then it pops out, fully formed, seemingly out of nowhere. Sometimes I don't feel it coming.

It's strange, but I feel like this is what you're talking about with unprompted thoughts.

Or just try to sit still for a minute and not do anything and you'll notice that the vast majority are unprompted and just arise from nowhere.

You would definitely have that level of control. These signals don't map to your inner monologue but they can pick up your intention to physically do something.

So if you think LEFT, you can move the selector on the keyboard to the next key to the left. And if you think CLICK, you can trigger a click. But you are focusing on asking your hand to physically make that click. Which your hand can't do obviously, but they can track those neurons to simulate the action for you.

I wonder how it works for those of us without an internal monologue.