nirvael

Kind of, Soundcloud has very aggressive copyright claims which is a problem for mixes.

I'm confused, surely there's a contradiction between "piracy was so good, we had this panacea of completely open, free, infinite music" and "streaming is bad even though it's the same infinite music library but we charge a small subscription". I get that artists aren't paid enough, but it's better than the $0 they get from piracy.

I actually had a similar idea that I cam across in my own research in brain-to-video applications. You could theoretically train the model in real-time by using brain data as a reward signal, such that the model would find the image or video that most strongly produces the desired response (e.g. an increase in certain brainwave bands associated with pleasure, or alertness, or fear).

I can imagine this has some very undesirable usecases if used in the wrong way.

Anyone have a link or more info on the "mind reading startup" being referred to?

Yeah you can email me (alex dot whelan at live dot co dot uk) or you can contact me through instagram (@aphynia)

I've been working on my own GAN for a while, trained on a few different datasets. Then the EEG data is fed into the GAN in real-time and used to interpolate within it's latent space. I assign each brainwave band (e.g. alpha, beta, etc.) to it's own point within that latent space, so the core idea is that as alpha increases (for example) the output heads towards that point in the space and that's reflected in the output image. Happy to talk more.

Using a Muse EEG headset to read brain activity and use that to drive the output of a GAN. Similar to other projects that try to visualise or decode thoughts, but at the moment it's an art project. Obviously quite limited by compute and hardware. I'm sort of looking for collaborators / co-founders / opportunities in the AI + neuroscience + creativity space.

Using a Muse EEG headset to read brain activity and use that to drive the output of a GAN. Similar to other projects that try to visualise or decode thoughts, but at the moment it's an art project. Obviosuly quite limited by compute and hardware. I'm sort of looking for collaborators / co-founders / opportunities in the AI + neuroscience + creativity space.

Yeah you're right I didn't think that through, why would you charge a battery while discharging another, just use the energy directly.

I'm sort of thinking out loud here but could you have two batteries running simultaneously but on opposite cycles, so while one is cooling the other is heating? Obviously it wouldn't be 100% efficient but it might reduce some wasted energy.

I was also confused by this. I think you're right, but in the original text they specifically mention a 'static background' that they remove, so it's not just a simple 'wrong way round' error, it's a fundamental misunderstanding of what's happening. Makes me wonder if the author actually knew what they were doing, or just using an LLM to vibe-code everything.

I considered it but the full OS route seemed cleaner, I wanted to use the Pi for it.