Why I'm bearish on mechanistic interpretability: the shards are not in the network — LessWrong
lesswrong.com · 5,754 words · saved by 1 readers
Once upon a time, the sun let out a powerful beam of light which shattered the world. The air and the liquid was split, turning into body and breath.…
x Why I'm bearish on mechanistic interpretability: the shards are not in the network — LessWrong Interpretability (ML & AI) Shard Theory AI Frontpage 24 Why I'm bearish on mechanistic interpretability: the shards are not in the network by tailcalled 13th Sep 2024 1 min read 40 24 Once upon a time, the sun let out a powerful beam of light which shattered the world. The air and the liquid was split, turning into body and breath. Body and breath became fire, trees and animals. In the presence of the lightray, any attempt to reunite simply created more shards, of mushrooms, carnivores, herbivores
related reading
- Gears in understanding — LessWronglesswrong.com
- A short note on interpretability and mindsericjmichaud.com
- interpreting GPT: the logit lens — LessWronglesswrong.com
- An Extremely Opinionated Annotated List of My Favourite Mechanistic Interpretability Papers v2 — AI Alignment Forumalignmentforum.org
- God Help Us, Let’s Try To Learn About Mechanistic Interpretability Techniquesastralcodexten.com
- What is the purpose of interpretability?ericjmichaud.com
- Maybe I was too harsh on deep learning theory (three days ago) — LessWronglesswrong.com
- A Mechanistic Explanation of Prompt Injection (and why you should study roles) — LessWronglesswrong.com
- Have You Tried Thinking About It As Crystals? — LessWronglesswrong.com
- An Extremely Opinionated Annotated List of My Favourite Mechanistic Interpretability Papers v2 — AI Alignment Forumalignmentforum.org
- Interpreting Language Model Parametersgoodfire.ai
- On Optimism for Interpretabilitygoodfire.ai