How much do you believe your results? - LessWrong

Thanks to Drake Thomas for feedback. • I. …

x How much do you believe your results? — LessWrong Best of LessWrong 2023 Goodhart's Law Probability & Statistics Epistemology Has Diagram Rationality World Modeling Curated 527 How much do you believe your results? by Eric Neyman 6th May 2023 Linkpost for ericneyman.wordpress.com 18 min read 19 527 Thanks to Drake Thomas for feedback. I. Here’s a fun scatter plot. It has two thousand points, which I generated as follows: first, I drew two thousand x-values from a normal distribution with mean 0 and standard deviation 1. Then, I chose the y-value of each point by taking the x-value and then a

saved by

• Blake Elias
• Trevor Trinh
• Sudarsh K
• Yudhister Joel Kumar
• Jo J.
• Will Anderson

related reading

• Beware The Man Of One Studyslatestarcodex.com
• Bits per Spike as a Betting Game · neurostatsblogneurostatsblog.github.io
• Minimal-trust investigationscold-takes.com
• How to Measure Anything — LessWronglesswrong.com
• A statistical approach to model evaluations \ Anthropicanthropic.com
• Knowing About Biases Can Hurt People — LessWronglesswrong.com
• Getting Eulered | Slate Star Codexslatestarcodex.com
• Why We Can't Take Expected Value Estimates Literally (Even When They're Unbiased) — LessWronglesswrong.com
• CAUSE, EFFECT, AND THE STRUCTURE OF THE SOCIAL WORLD. MEGAN T. STEVENSONbu.edu
• Why we can't take expected value estimates literally (even when they're unbiased) - The GiveWell Blogblog.givewell.org
• Bayesian Mindsetcold-takes.com
• Your intuitions are not magic — LessWronglesswrong.com