flâneur — a map of the web's best reading

Mechanistic Interpretability is Being Pursued for the Wrong Reasons — LessWrong

lesswrong.com · 2,360 words · saved by 1 readers

The success of prosiac A.I. seems to have generally surprised the rationalist community, including myself. Rationalists have correctly observed that…

x Mechanistic Interpretability is Being Pursued for the Wrong Reasons — LessWrong AI Frontpage 18 Mechanistic Interpretability is Being Pursued for the Wrong Reasons by Cole Wyeth 4th Jul 2023 Linkpost for colewyeth.com 8 min read 1 18 The success of prosiac A.I. seems to have generally surprised the rationalist community, including myself. Rationalists have correctly observed that deep learning is a process of mesa-optimization; stochastic gradient descent by backpropogation finds a powerful artifact (an artificial neural net or ANN) for a given task. If that task requires intelligence, the a

Explore this link on the map →

related reading