Daniel Paleka: AI safety takes | Substack

Better version of the monthly Twitter thread. Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models Not all paths lead to ROME. Apparently, knowing where a fact is stored doesn’t help with amplifying or…

Jan 31

Better version of the monthly Twitter thread. Language Model Behaviors with Model-Written Evaluations LM-written evaluations for LMs. Automatically…

Jan 4

Better version of the monthly Twitter thread. Adversarial Policies Beat Professional-Level Go AIs Adversarial policies in Go. Policies trained on…

Dec 1, 2022

This is Daniel Paleka: AI safety takes, a newsletter about AI/ML safety research.

Nov 30, 2022

Daniel Paleka: AI safety takes

About Archive Sitemap

#nojs-banner { position: fixed; bottom: 0; left: 0; padding: 16px 16px 16px 32px; width: 100%; box-sizing: border-box; background: red; color: white; font-family: -apple-system, "Segoe UI", Roboto, Helvetica, Arial, sans-serif, "Apple Color Emoji", "Segoe UI Emoji", "Segoe UI Symbol"; font-size: 13px; line-height: 13px; } #nojs-banner a { color: inherit; text-decoration: underline; } This site requires JavaScript to run correctly. Please turn on JavaScript or unblock scripts