niplav @niplav@schelling.pt

Agency is just counterfactual convergent instrumentality

Agency is just subjectively-indexical Vingean uncertainty

the sludge club

Swipor theory

hoooly crap the tino rangatiratanga is a good flag

closest pairs of points are not necessarily reflexive. there are some points in euclidean space that are just fundamentally abandoned

“perception is all you need” — Rosenblatt, 1958

it'd be deeply ironic if MLPs, sufficiently scaled, are enough for AGI

A group of niplavs is called a NeurIPS

Death with Dignity poast was net negative, it's now the number one thing EAs outside of AI alignment have read,and gives a *really* wrong vibe. Like, fine, I read it and that was OK bc ~~context~~ but someone whose only exposure to AI alignment was some 80k podcast episodes & reading karnofsky comes away with a wrong image & plan

Knowing about cog biases helps with rationality, there's just a sampling bias when looking at people who argue on the internet who refer to them

Needed: self aware ironic supervillain who is nevertheless cringe

Believable negative utilitarian supervillain

MOSFEM

OK submitted to review

A machine-executable plan to install a self-supervised reinforcement learning system on all instances of the spot robot from boston dynamics, described step by step | posted on art station