Skip to main content
Scour
Browse
Getting Started
Login
Sign Up
You are offline. Trying to reconnect...
Close
Copied to clipboard
Close
Unable to share or copy to clipboard
Close
🎯 Rationalism
effective altruism, LessWrong, reasoning, epistemic
Filter Results
Timeframe
Fresh
Past Hour
Today
This Week
This Month
Feeds to Scour
Subscribed
All
Scoured
21221
posts in
56.4
ms
Reflectively stable
consequentialists
are expected utility
maximisers
🔀
Choice Architecture
lesswrong.com
·
4d
Why LLM Agents Fail: Four Mechanisms of Cognitive
Decay
and the Reasoning
Harness
Layer
🧠
LLM Reasoning
dev.to
·
1d
·
DEV
"
Leader-Motivated
Behavior: Voting by Mail in the 2020 General Election" #
ELB
🗳️
Elections
electionlawblog.org
·
3h
Are you paying an AI ‘
swarm
tax’? Why single agents
often
beat complex systems
🕵️
AI Agents
oodaloop.com
·
2d
Mind the van
Emden
Gap
🧠
LLM Reasoning
blog.fogus.me
·
5d
·
Lobsters
,
Hacker News
AI as a
fascist
artifact
🎭
Anthropic Claude
osnews.com
·
2d
·
Hacker News
not much
happened
today
✍️
Prompt Engineering
news.smol.ai
·
4d
Roko
's
basilisk
may work on humans
🧠
Rationality
lesswrong.com
·
13h
Are you paying an AI ‘
swarm
tax’? Why single agents
often
beat complex systems
🕵️
AI Agents
venturebeat.com
·
4d
Why LLM
Reasoning
Is Breaking AI Infrastructure (And How to Fix It)
🧠
LLM Reasoning
dev.to
·
2d
·
DEV
Quiz
Game challenge
⬛
Go (game)
quiz-game-bay-three.vercel.app
·
4d
·
DEV
"Bad faith" means
intentionally
misrepresenting
your beliefs
🎭
Persuasion
lesswrong.com
·
4h
Scientific datasets are
riddled
with
copy-paste
errors
📰
RSS Reading Practices
metafilter.com
·
6d
AI 101: How Token
Taxonomy
Affects
Your Bill
💰
Tokenomics
turingpost.com
·
4d
Stop Building One
Giant
Prompt
: A Better Way to Design LLM Systems
🧠
Context Engineering
dev.to
·
1d
·
DEV
Deep Learning Weekly: Issue 452
🖥️
Local AI
deeplearningweekly.com
·
3d
Can you build a public debate platform that rewards argument quality over
tribal
affiliation
? I've been trying to.
🎭
Persuasion
lesswrong.com
·
7h
OpenAI says GPT-5.5's improvements are
strongest
in agentic coding, computer use, and early scientific research, which require reasoning across longer
contexts
...
🧠
OpenAI
techmeme.com
·
3d
ejentum/eval
: A/B evaluate any LLM task with and without
Ejentum
cognitive injection. n8n workflow + TypeScript module.
📊
LLM Evaluation
github.com
·
4d
·
DEV
Communicating
with people who
disagree
on "obvious" things
🎭
Persuasion
lesswrong.com
·
2d
Page 2 »
Log in to enable infinite scrolling
Keyboard Shortcuts
Navigation
Next / previous item
j
/
k
Open post
o
or
Enter
Preview post
v
Post Actions
Love post
a
Like post
l
Dislike post
d
Undo reaction
u
Save / unsave
s
Recommendations
Add interest / feed
Enter
Not interested
x
Go to
Home
g
h
Interests
g
i
Feeds
g
f
Likes
g
l
History
g
y
Changelog
g
c
Settings
g
s
Browse
g
b
Search
/
Pagination
Next page
n
Previous page
p
General
Show this help
?
Submit feedback
!
Close modal / unfocus
Esc
Press
?
anytime to show this help