Limits to Legibility — LessWrong
From time to time, someone makes the case for why transparency in reasoning is important. The latest conceptualization is Epistemic Legibility by Eli…
x Limits to Legibility — LessWrong Epistemology Tacit Knowledge Rationality World Modeling Frontpage 168 Limits to Legibility by Jan_Kulveit 29th Jun 2022 6 min read 12 168 From time to time, someone makes the case for why transparency in reasoning is important. The latest conceptualization is Epistemic Legibility by Elizabeth, but the core concept is similar to reasoning transparency used by OpenPhil, and also has some similarity to A Sketch of Good Communication by Ben Pace. I'd like to offer a gentle pushback. The tl;dr is in my comment on Ben's post, but it seems useful enough for a standa
related reading
- Legible vs. Illegible AI Safety Problems — LessWronglesswrong.com
- How An Algorithm Feels From Inside — LessWronglesswrong.com
- How To Write Quickly While Maintaining Epistemic Rigor — LessWronglesswrong.com
- Deep Deceptiveness — LessWronglesswrong.com
- A Sketch of Good Communication — LessWronglesswrong.com
- the case for CoT unfaithfulness is overstated — LessWronglesswrong.com
- Illusion of Transparency: Why No One Understands You — LessWronglesswrong.com
- How To Go From Interpretability To Alignment: Just Retarget The Search — LessWronglesswrong.com
- Local Validity as a Key to Sanity and Civilization — LessWronglesswrong.com
- What Are You Tracking In Your Head? — LessWronglesswrong.com
- The Best of LessWrong — LessWronglesswrong.com
- How AI Is Learning to Think in Secretnickandresen.substack.com