niplav @niplav@schelling.pt

extra-punish people who euler you without anything backing it up

get in loser, we're evolving to extinction

there's some IOIs it's a crime not to react to

For this: https://twitter.com/nabla_theta/status/1633866526720954370

just keeps on giving

I might actually be able to say something about the computational complexity of achieving von Neumann-Morgenstern coherent goals

a list of all known bounds on price of anarchy/price of stability

be like the missile

have low indexical uncertainty

In which niplav undertakes the easy step of formalising a concept:

https://niplav.github.io/notes#The_Price_of_Inadequacy

which

is the computer that chatgpt is running on conscious?

is chatgpt conscious

Capabilities idea: bf83a0cb25bb227743a9fc877a02571dca55d204

the longer you were uncertain about a thing, the stronger the reward upon discovering its true nature

is this just reinventing the powerseeking theorems? gotta check

it would be helpful if we knew whether for almost all random functions from ℝⁿ→ℝ, changing any one element of the domain slightly changes the output a lot

then one might also prove (or disprove) the same thing for functions implementable by some classes neural networks

the eigenluigi