Post

good thread by someone smarter than me explaining that AI interpretability explainer:

Colin@colin-fraser.net

ok having read it, let me try. Background knowledge: a neural network, conceptually, has billions of little things called neurons. One goal of so-called "interpretability" would be to be able to look at each neuron and say what it does for the network.

Will Oremus

@willoremus.com

my brilliant colleague @matteowong.bsky.social also wrote in plain terms about the ai interpretability blog post, why it matters, and how it's dividing experts in the field: www.theatlantic.com/technology/2...

theatlantic.comThe Blog Post That Set the AI World on FireAn incendiary post from a prominent researcher suggests that AI is actually more predictable than we thought.

17/10/26, 1:45 am4 reposts19 likes

No replies yet.