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.

Tag: honesty

Minutes:
Pick a custom range (minutes). Leave a field empty for no limit.
Blog:
Year:
2026
2025
2024
2023
2022
2021
2020
2019
2018
2017
2016
2015
2014
2013
Tags:
Filter by tag...
Exclude tag...
5212 tags
Links:
Filter by linked site (twitter, substack…)
2 posts found
Compact Mode
Save Reads
Apr 21, 2026
acx
Read on
41 min 6,219 words 223 comments 803 likes podcast (33 min)
Scott Alexander provides fifteen pieces of writing advice for aspiring bloggers, emphasizing authenticity, avoiding microdishonesty, mastering basic disciplines before breaking rules, and finding original angles on common topics rather than recycling blogosphere content. Longer summary
Scott Alexander offers fifteen pieces of writing advice for participants in Lighthaven's Inkhaven blogging bootcamp, covering topics from avoiding microdishonesty to finding original angles on common subjects. He discusses the importance of authenticity in writing, warns against clichés while acknowledging their ubiquity, and introduces the concept of 'mountaintop disciplines'—strict writing rules to master before breaking them. The advice spans structural concerns like avoiding tangled sentences and the traditional five-paragraph essay, to strategic considerations like injecting first-hand knowledge rather than recycling blogosphere topics, and tactical tips about using conflict and mystery to maintain reader interest. Throughout, Scott emphasizes that good writing comes from genuine contact with the world and honest expression of one's actual thoughts, rather than attempting to say what seems presentable or expected. Shorter summary
Jan 09, 2024
acx
Read on
19 min 2,920 words 346 comments 218 likes podcast (20 min)
Scott reviews two papers on honest AI: one on manipulating AI honesty vectors, another on detecting AI lies through unrelated questions. Longer summary
Scott Alexander discusses two recent papers on creating honest AI and detecting AI lies. The first paper by Hendrycks et al. introduces 'representation engineering', a method to identify and manipulate vectors in AI models representing concepts like honesty, morality, and power-seeking. This allows for lie detection and potentially controlling AI behavior. The second paper by Brauner et al. presents a technique to detect lies in black-box AI systems by asking seemingly unrelated questions. Scott explores the implications of these methods for AI safety and scam detection, noting their current usefulness but potential limitations against future superintelligent AI. Shorter summary
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.