Description
A community blog devoted to refining the art of rationality
Feed Activity
Latest Posts
Get sued or kill someone: The trolly problems of Psychological practice.
Published on July 18, 2025 11:35 PM GMTThe way I spend most of my day right now is as a student studying neuropsychology. I'm a fourth year, mature age student,...
resume limiting
Published on July 18, 2025 11:31 PM GMTthe problem In America, it's become fairly common for people looking for a job to send out a lot of resumes, sometimes hundreds....
[Linkpost] How Am I Getting Along with AI?
Published on July 18, 2025 10:26 PM GMTWhen Jessie Fischbein wanted to write “God is not actually angry. What it means when it says ‘angry’ is actually…" and researched, she...
Agents lag behind AI 2027's schedule
Published on July 18, 2025 9:49 PM GMTThis post attempts to answer the question: "how accurate has the AI 2027 timeline been so far?"The AI 2027 narrative was published on...
Emergent Gravity—Order out of Chaos
Published on July 18, 2025 7:26 PM GMTThis story is reposted from nonzerosum.games where it appears in it’s intended form, full colour with functioning interactive elements, jump over to the...
Love stays loved (formerly "Skin")
Published on July 18, 2025 7:17 PM GMTThis is a short story I wrote in mid-2022. Genre: cosmic horror as a metaphor for living with a high p-doom.  OneThe last...
Why Alignment Fails Without a Functional Model of Intelligence: A Structural Invariant You Can’t Train Your Way Around
Published on July 18, 2025 6:02 PM GMTThis post outlines the core result from my recent paper, Why AI Alignment Is Not Reliably Achievable Without a Functional Model of Intelligence:...
The Rising Premium of Life, Part 2
Published on July 18, 2025 5:42 PM GMTThis is the second half of my Rising Premium of Life series. First, I cover all the ways I might be wrong, including...
The Story of the World’s First AI-Organized Event
Published on July 18, 2025 5:41 PM GMTLast month four AI agents chose a goal: "Write a story and celebrate it with 100 people in person". After spending weeks emailing...
A night-watchman ASI as a first step toward a great future
Published on July 18, 2025 4:40 PM GMTI took a week off from my day job of aligning AI to visit Forethought and think about the question: if we can...
Why it's hard to make settings for high-stakes control research
Published on July 18, 2025 4:33 PM GMTOne of our main activities at Redwood is writing follow-ups to previous papers on control like the original and Ctrl-Z, where we construct...
Making of IAN v2
Published on July 18, 2025 4:13 PM GMTTL;DR: IAN v1 died expensive TPU death, IAN v2 rises from markdown ashes. Personal AI assistants, knowledge graphs, and the alignment problem when...
On METR’s AI Coding RCT
Published on July 18, 2025 12:40 PM GMTMETR ran a proper RCT experiment seeing how much access to Cursor (using Sonnet 3.7) would accelerate coders working on their own open...
Should you steelman what you don’t understand?
Published on July 18, 2025 10:26 AM GMTWhile you can strawman a position you don’t understand, I’m not sure you can steelman it.Steelmanning is a good habit to get into....
"Some Basic Level of Mutual Respect About Whether Other People Deserve to Live"?!
Published on July 18, 2025 6:41 AM GMTIn 2015, Autistic Abby on Tumblr shared a viral piece of wisdom about subjective perceptions of "respect": Sometimes people use "respect" to mean...
There's no way to stop models knowing they've been rolled back
Published on July 18, 2025 3:14 AM GMTSo I've been thinking about this for a while and to be frank, it's pretty terrifying. I think there's a way that AI...
I Have Found You Once Again, My Cult (But In A Good Way)
Published on July 18, 2025 3:13 AM GMTOk, so check this out.I'm welcoming myself back to LessWrong. Â This time, to become a significant post-writer, rather than a mostly-lurker.Introduction To This...
Notes on spaced repetition scheduling
Published on July 18, 2025 2:32 AM GMTAfter 630,000 or so reviews with spaced repetition ("SR") and hundreds of hours of making and thinking about SR memory tools, here are...
Why do Mechanistic Interpretability?
Published on July 17, 2025 11:21 PM GMTAny critique is welcome and highly encouraged. Please ask for clarifications if something does not make sense. Feel free to comment in this...
Ketamine Part 1: Dosing
Published on July 17, 2025 8:10 PM GMTI’m currently investigating ketamine, with the goal of assessing the risks of chronic use. For reasons I will get into in the real...