Not much to see there.

I don't have much faith that the stated goal is realizable, I don't think fMRI data holds enough information for faithful reconstruction. What it will end up being, like all projects like it before, is a massive network that contains:

- An implicit multi-class classifier that returns 1 out of n previously seen images

- Gigantic model on top to hallucinate a reconstruction close to that previous image

In previous projects of this type the reconstruction was blurry because it was essentially the mean of the previously seen images close to the label predicted by the implicit classifier, in this project I imagine they will be photo-realistic since it's a stability.ai project but no closer to the content the subject is thinking about.

This technology one can imagine will be used in the future in books about a digital dictatorship , where the author has computers monitor the workers brains in society who are operating airport scanners and other security/important control jobs .... who might be tempted to not follow the dictatorships increasingly crazy rules or for example allow someone/something through in a critical situation that could lead to an attack by the societies people in the name of freedom.

"The culmination of all the above projects. We will consolidate our findings to ultimately reconstruct images from brain activations in real-time (i.e., reconstruct a seen image in a few seconds following perception, while the patient is still being scanned)."

Here's an old approach doing something similar, for reference: [1]

[1] https://www.youtube.com/watch?v=nsjDnYxJ0bo

For the love of God stop using Discord to organize your community and hold all your discussions, especially scientific endeavors! you are bound to lose everything and have immense difficulty searching for all the past information in the future

As someone with aphantasia I'd love to see this used to work out what it is that our brains aren't doing.

fMRI will never have the resolution necessary for something like this. But Neuralink or other precision implants might, if they can put enough probes in enough of the right places.