Archive - A Flood of Ideas

Polygon, Chapter 1

In which we meet our protagonist on maybe not the worst day of her career

Apr 24 •

January 2025

Thoughts on RLHF

Subtitle: CS120 Week 2, Lecture 1 - Reward Functions, Alignment, and Human Preferences

Jan 23 •

Your AI Safety focus is downstream of your AGI timeline

Crossposted to LessWrong

Jan 17 •

October 2024

Mitigating Failures in AI Agents and Multiagent Systems

Probabilistic Outputs, Failures States, and Degree of Trust

Oct 18, 2024 •

111 subscribers, time to figure out what people are here for

Oct 9, 2024 •

Know Thyself, maybe

Or maybe don't...

Oct 6, 2024 •

A reminiscence from college days

Oct 4, 2024 •

September 2024

AI Podcast Discusses My Essays

Sep 18, 2024 •

14:46

August 2024

July 2024

What I want in an AI agent

Desirable traits for local artificial general intelligence

Jul 26, 2024 •

#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