niplav @niplav@schelling.pt

what *I* took away from it is that Searle doubts chinese people are conscious

wait, is CIRL incorrigible *for the same reason* that utility-maximizers don't wirehead?

https://niplav.github.io/notes.html#An-Example-for-Not-Updating-Uncertain-Utility-Functions

if your eag profile doesn't say 'neartermism', you'll automatically be drafted into the deepmind potential hires mailing list

“The problem with Marcus' argument is that the only alternative to statistical AI is spiritual AI“ no what the fuck why would you say this did you even read the sequences i don't even know where to start with that

holy fuck were ACX comments always this bad? most of them are fucking atrocious. like, barely tolerable.

at least i'm up to a level sunkcostfalacially where i'm reading a comment on an acx post and someone uses “consciousness” and i'm hella out there real quick

to what extent did AlphaFold2 solve protein folding? there should be a writeup of how much & what needs to be done for it to be completely solved.

solarpunk slightly hindered by the fact that for solar panels and cutesy robots you need industrial-strength chipfabs that are so advanced we have like 6 of them in the entire world

a “moron” could also be a group-theoretic structure. “On the symplectic inverses of left-invariant morons”

morad and moroid

watching my motivational system surfing the edge of the indefference point on the hyperbolic discounting line—always pulled back by my good friend, the cost

once i've found a core to corrigibility i'll write an incel manifesto

https://nitter.hu/lastpositivist/status/1534952549077360641#m instrumental convergence

every xenofem.me user be like

> being in excruciating agony is based actually