Around 1993, Microsoft began talking to cable companies to make something called "Cablesoft." The ideas was, the internet was slow, clunky, and untrusted for things like commerce. Cable was fast, Microsoft had great tech, they were going to create a corporate "information superhighway" to replace the internet. This sounds very dumb now, but what made this so compelling was they were controlling UX through the TV. The thought was, a TV is SO much better than a crappy computer and it's in the den of every home in America. It was the massive, odds on favorite to win everything. Why didn't it? Because the open nature of the internet encouraged innovation at the edges. Look at the UX on your iPhone today. It simply wasn't possible to dream that up then. Crypto is in its Cablesoft era today. I am begging you all to remember that we are all here because banks suck and should get disrupted. Do not give up AT the finish line and let the bad behavior of the last few years destroy your optimism. Open systems beat closed systems, TradFi won't win everything, keep the faith.

This works really well btw, at the end of your query ask your LLM to "structure your response as HTML", then view the generated file in your browser. I've also had some success asking the LLM to present its output as slideshows, etc. More generally, imo audio is the human-preferred input to AIs but vision (images/animations/video) is the preferred output from them. Around a ~third of our brains are a massively parallel processor dedicated to vision, it is the 10-lane superhighway of information into brain. As AI improves, I think we'll see a progression that takes advantage: 1) raw text (hard/effortful to read) 2) markdown (bold, italic, headings, tables, a bit easier on the eyes) <-- current default 3) HTML (still procedural with underlying code, but a lot more flexibility on the graphics, layout, even interactivity) <-- early but forming new good default ...4,5,6,... n) interactive neural videos/simulations Imo the extrapolation (though the technology doesn't exist just yet) ends in some kind of interactive videos generated directly by a diffusion neural net. Many open questions as to how exact/procedural "Software 1.0" artifacts (e.g. interactive simulations) may be woven together with neural artifacts (diffusion grids), but generally something in the direction of the recently viral There are also improvements necessary and pending at the input. Audio nor text nor video alone are not enough, e.g. I feel a need to point/gesture to things on the screen, similar to all the things you would do with a person physically next to you and your computer screen. TLDR The input/output mind meld between humans and AIs is ongoing and there is a lot of work to do and significant progress to be made, way before jumping all the way into neuralink-esque BCIs and all that. For what's worth exploring at the current stage, hot tip try ask for HTML.