Want to dive into Scott Alexander's work and his thousands of blog posts? This fan website lets you sort and do semantic search through the whole codex. Enjoy!

See also Top Posts and All Tags.

Or pick a range
–
min
Blog
Only
Year
2026
2025
2024
2023
2022
2021
2020
2019
2018
2017
2016
2015
2014
2013
Tags
Browse all 5386
Include tag...
Exclude tag...
Links to
Filter by linked site (twitter, substack…)
Remember which posts I've read on this device
2 posts
Date
Length
Likes
Comments
AI safety (77) AI alignment (37) Anthropic (15) neural networks (12) Claude (9) AI consciousness (8) AI interpretability (3) mechanistic interpretability (3)

God Help Us, Let’s Try To Learn About Mechanistic Interpretability Techniques

Scott explains current mechanistic interpretability techniques for understanding AI cognition, from linear probes to emotion vectors, showing they're useful for monitoring but insufficient for controlling AI behavior or ensuring safety.

acx
Sep 8, 2026 5,570 words 471 likes 274 comments Read Read
AI safety (77) AI alignment (37) evolution (16) deception (5) mesa-optimizers (2) prosaic alignment (2)

Deceptively Aligned Mesa-Optimizers: It's Not Funny If I Have To Explain It

Scott Alexander explains mesa-optimizers in AI alignment, their potential risks, and the challenges of creating truly aligned AI systems.

acx
Apr 11, 2022 3,483 words 119 likes 309 comments Listen · 27 min Read Read
Per page:
Showing 1 to 2 of 2 results
Get these search results in an EPUB

Your filters match 2 posts.

Posts to include
–
Leave empty to keep the defaults. Range cannot exceed 500 posts.
Download now

Generates an EPUB right now and downloads it to your device.

Send to email

Generates an EPUB in the background and emails you a temporary download link.

Your email is not shared with anyone.

Email address

To send to your Kindle, just use this link.