nature.com/articles/s41586-026-10759-2

so what’s the next step

back to rl

oops

wait we’re off-topic

ok so quantum supremacy...

lol

i’m busy

someone google it

idk

link?

i think it’s on arxiv

oh right

the one about rl for qec

wait what’s the paper again

or cursed

if we’re lucky

but rl can handle it

so curse of dimensionality strikes again

exponentially huge

it’s a mess

uhhh...

what’s the state space even look like

ok but seriously

why not

haha sanity check in rl

or like... a sanity check layer

so we need regularization

good point

like... overfitting to noise?

but what if it learns bad habits