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
related reading
- An Ambitious Vision for Interpretability — AI Alignment Forumalignmentforum.org
- A Pragmatic Vision for Interpretability — AI Alignment Forumalignmentforum.org
- An Extremely Opinionated Annotated List of My Favourite Mechanistic Interpretability Papers v2 — AI Alignment Forumalignmentforum.org
- How To Go From Interpretability To Alignment: Just Retarget The Search — LessWronglesswrong.com
- A Pragmatic Vision for Interpretability — LessWronglesswrong.com
- Deep Deceptiveness — LessWronglesswrong.com
- You can’t imitation-learn how to continual-learn — LessWronglesswrong.com
- God Help Us, Let’s Try To Learn About Mechanistic Interpretability Techniquesastralcodexten.com
- On Optimism for Interpretabilitygoodfire.ai
- What is the purpose of interpretability?ericjmichaud.com
- Deep learning as program synthesis — LessWronglesswrong.com
- Maybe I was too harsh on deep learning theory (three days ago) — LessWronglesswrong.com