Against Almost Every Theory of Impact of Interpretability — LessWrong
Charbel-Raphaël argues that interpretability research has poor theories of impact. It's not good for predicting future AI systems, can't actually aud…
x Against Almost Every Theory of Impact of Interpretability — LessWrong Best of LessWrong 2023 Interpretability (ML & AI) AI Frontpage 336 Against Almost Every Theory of Impact of Interpretability by Charbel-Raphaël 17th Aug 2023 AI Alignment Forum 31 min read 93 336 Ω 96 Epistemic Status: I believe I am well-versed in this subject. I erred on the side of making claims that were too strong and allowing readers to disagree and start a discussion about precise points rather than trying to edge-case every statement. I also think that using memes is important because safety ideas are boring and an
Explore this link on the map →related reading
- Against Almost Every Theory of Impact of Interpretability — AI Alignment Forumalignmentforum.org
- Dario Amodei — The Urgency of Interpretabilitydarioamodei.com
- A Pragmatic Vision for Interpretability — AI Alignment Forumalignmentforum.org
- Neel Nanda on Mechanistic Interpretability: Progress, Limits, and Paths to Safer AI — EA Forumforum.effectivealtruism.org
- The Hitchhiker's Guide to Actionable Interpretabilityactionable-interpretability-guide.github.io
- How Can Interpretability Researchers Help AGI Go Well? — AI Alignment Forumalignmentforum.org
- On Optimism for Interpretabilitygoodfire.ai
- Interpretability Will Not Reliably Find Deceptive AI — AI Alignment Forumalignmentforum.org
- An Ambitious Vision for Interpretability — AI Alignment Forumalignmentforum.org
- Research Areas in Interpretability (The Alignment Project by UK AISI) — AI Alignment Forumalignmentforum.org
- How To Become A Mechanistic Interpretability Researcher — AI Alignment Forumalignmentforum.org
- Interpretability Will Not Reliably Find Deceptive AI — LessWronglesswrong.com