Unless you're posing a non-smooth model where we're keeping them at bay now but they'll increase later on?
This is what the "alignment is hard" people have been saying for a long time. (Some search terms here include "treacherous turn" and "sharp left turn")
https://www.lesswrong.com/w/treacherous-turn
A central AI alignment problem: capabilities generalization, and the sharp left turn
(my bad, hadn't read the post at the time I commented so this presumably came across cluelessly patronizing)
Seems coherent, my skeptical brain next asks "how do we know you are learning to distinguish fine-grained attention, instead of confabulating a new type of thing?"
Good question! Your experience is entirely normative.
Also I'm not 100% sure what "normative" means in this context.
attention. The part of your consciousness you are paying attention to. Attention can be in only one place at a time.
This feels... intuitively sort-of-but-not-actually-true, depending on what you mean by it.
Right now, I'm paying attention to these words I'm typing, and I'm also dimly aware of my shoulders being in pain. When I direct my attention a bit more to my shoulder... well, there are a lot of parts of my shoulders (there's also a lot of parts of the words I'm typing)
and in some sense only one gets to be "the thing I'm paying attention to" but, "thing to pay attention to" also isn't really a coherent concept since they contain multitudes. That seems like the sort of thing I'd expect Buddhism to care about.
What say you?
Followup thought: there's a lot you can do as a side hustle. If you can get a job that you don't care that much about but pays well, and you don't have enough money to quit with 3+ years of runway (i.e. 2+ for Doing Stuff and 1 for figuring out how to have more money)...
...that doesn't mean "don't do anything", it means "find things to do that are motivating enough you can do them in evenings/weekends and start building some momentum/taste. (This may also later help you get a AI safety job.)"
Most people who end doing jobs that they love / are meaningful to them find some way to pursue it during their spare time while they have a Real Job.
1See also: if you aren't financially stable, rather than "earn to give", "earn to get sufficiently wealthy you can afford to not have a job for several years while working on AI stuff".
BTW, I think "financial stable" doesn't mean "you can technically survive awhile" it's "you have cushion that you will not feel any scarcity mindset." For almost everyone I think this means at least 6 months more runway than you think you plan to use, and preferably more like a year.
(Note, AI automation might start doing wonky things to job market by the time you're trying to get hired again, if you run out of money)
I also don't really recommend people try to do this as their first job. I think there's a collection of "be a competent adult" skills that you probably don't have yet right out of college, and having any kind of job-with-a-boss for at least like 6 months is probably valuable.
3
2I have only read the first paragraph or two, but, would like the all-things-considered "how good is this?". I went into Sleep No More with literally zero spoilers and I liked it that way.
When obsolescence shall this generation waste,
The market shall remain, in midst of other woe
Than ours, a God to man, to whom it shall say this:
"Time is money, money time,---that is all
Ye know on earth, and all ye need to know."
This feels like it's referencing something literary I don't know, curious if that's correct
(I think would be good to copy-paste here for ease of reference)
Well in its defense a paragraph later we have:
Corpses don't cause atrocities.
apologies, I hadn't actually read the post at the time I commented here.
In an earlier draft of the comment I did include a line that was "but, also, we're not even really at the point where this was supposed to be happening, the AIs are too dumb", I removed it in a pass that was trying to just simplify the whole comment.
But as of last-I-checked (maybe not in the past month), models are just nowhere near the level of worldmodeling/planning competence where scheming behavior should be expected.
(Also, as models get smart enough that this starts to matter: the way this often works in humans is human's conscious planning verbal loop ISN'T aware of their impending treachery, they earnestly believe themselves when they tell the boss "I'll get it done" and then later they just find themselves goofing off instead, or changing their mind)