There should be some teeth, but also we should be prepared for a small amount of "unfairness" baked into the system. If there are no controls, everyone will cheat. But if there's too many obstacles (turnstiles, checkpoints, conductors, cameras, etc) then people won't want to ride.
People like what they like, so if that's not your jam I wouldn't sweat it. That said, Moby Dick is perhaps a poor example of "literature" to start on if you're not sure you like "literature", mostly from being so long. If I might recommend trying Cosmicomics by Italo Calvino, or The Cyberiad by Stanislaw Lem, as they are easy to dip in and out of are nominally "sci fi" while still laying some claim to "literature". Lem and Calvino may lead you to Borges or PKD or Ursula K LeGuin or China Mieville - more genre artists that arguably aspire to being more than pulp.
I get this sentiment, but I think there's probably a LOT of people who are doing good things, cool things, helpful things, who are helped by Al Gore's free and open Internet. But most of them don't bother to upvote, or post a "thank you" or anything because the medium makes everything so frictionless. It's only the OSS zealots and the people who have issues who you'll hear from. The vocal minority. It's kinda shitty, but learning to ignore the haters and bad actors is table stakes. But feeding AI farms is the new threat, and that' definitely something unsolved. Going dark is certainly a solution. Small enclaves of invite-only blogs and tweets, I guess...
Your entire nervous system is in a constant loop polling the external world. Add that to current AIs and see what happens.
Honestly, though, the next big thing that needs to happen is proper "learning" in real-time. Allow for training (weight modulation) and queries to happen simultaneously. That's the full package.
Finally! Someone who actually "gets it" about what makes these things not alive, sentient, or conscious! They don't have the constant continuous "input" of multiple senses feeding their constantly thinking/dreaming/learning-in-realtime system (that they don't have), and as mentioned by the parent comment to yours, they don't do anything when not actively processing a prompt (so there's no dreaming, planning, thinking, or whatever else going on the the static pile of numbers sitting there in memory or on the hard drive).
Make the "thinking" parts continually active, fed constant input (of multiple types/senses) and always in "learning" mode (adding/updating model weights in realtime) and then you might start to lean in the right direction for AGI/ASI/consciousness of some sort.
I’m very interested in this approach. I’ve hosted friends’ websites for decades but I’ve been the single-point of failure, so “cooperative” is very enticing.
I’m currently working on a cooperative “lights-on” solution which might be complementary.
I don't know much about the SSH this app uses (Citadel) which uses NIOSSH under the hood. I prefer using Mosh (https://github.com/mobile-shell/mosh) for mobile apps where connectivity is often spotty. Does NIOSSH use a model that accounts for that?
NIOSSH itself doesn't include Mosh support, so adding it would require a mosh client. i didn't include it in the initial beta, because mosh isn't direct fit for tmux control mode, which requires an ordered raw byte stream. i'm planning to add mosh for standalone terminal sessions tho.
