Skip to main content
Scour
Discover
Docs
Login
Sign Up
Discover
About
Docs
Changelog
You are offline. Trying to reconnect...
Copied to clipboard
Unable to share or copy to clipboard
AI Alignment
🎯 AI Alignment
Value Learning, RLHF, Constitutional AI, Safety Research
Filter Results
Timeframe
Choose a timeframe
Fresh
Past Hour
Today
This Week
This Month
Feeds to Scour
Subscribed
All
Scoured
53
posts in
34.6
ms
⚖️
Ethics
ft.com
·
3d
3 days ago
Letter: Argentina’s
AI
fix widens the gap it is meant to close
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Letter: Argentina’s AI fix widens the gap it is meant to close
🧠
LLM Training
fareedkhan-dev.github.io
·
23h
23 hours ago
Train LLM from Scratch
Discussed on
Hacker News
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Train LLM from Scratch
🛡️
AI Safety
medium.com
·
1d
1 day ago
What I
Learned
Studying Whether Fine-Tuning Breaks a Transformer’s “Copy
Mechanism
”
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for What I Learned Studying Whether Fine-Tuning Breaks a Transformer’s “Copy Mechanism”
🛡️
AI Safety
lesswrong.com
·
2d
2 days ago
A brief list of ways
AI
safety
efforts could be net negative
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for A brief list of ways AI safety efforts could be net negative
🚀
Frontier AI
Ethereum Research
·
6d
6 days ago
The Voice of Silence Beyond
Alignment
: Human Sovereign Will as the Missing Layer in AGI Governance
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for The Voice of Silence Beyond Alignment: Human Sovereign Will as the Missing Layer in AGI Governance
⚖️
AI Regulation
GitHub
·
2d
2 days ago
Show HN: I built an 11-LLM consensus engine to detect
AI
hallucination
Covers
Show HN: An AI that reliably builds full-stack apps by preventing LLM mistakes
Discussed on
Hacker News
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Show HN: I built an 11-LLM consensus engine to detect AI hallucination
🤖
AI
day1training.com
·
4d
4 days ago
Distributed
AI
on AWS
Discussed on
Hacker News
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Distributed AI on AWS
🔬
Anthropic
dw.com
·
2d
2 days ago
US curbs Anthropic
AI
access, raising global concerns
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for US curbs Anthropic AI access, raising global concerns
🎯
RLHF
Interconnects
·
5d
5 days ago
Frontier post-training recipe review with Finbarr Timbers
Covers
10 stories
See all stories this covers
including
DeepSeek-V3 Technical Report
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Frontier post-training recipe review with Finbarr Timbers
🔬
Anthropic
lesswrong.com
·
2d
2 days ago
How I think developers of frontier
AI
systems and regulators ought to act in the face of existential
AI
risk
Covers
2 stories
See all stories this covers
including
[2212.08073] Constitutional AI: Harmlessness from AI Feedback
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for How I think developers of frontier AI systems and regulators ought to act in the face of existential AI risk
🔓
Open Source AI
Import AI
·
6d
6 days ago
Import
AI
461: “
Alignment
is not on track”; FrontierCode; and synthetic
research
interns
Covers
2 stories
See all stories this covers
including
Introducing FrontierCode
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Import AI 461: “Alignment is not on track”; FrontierCode; and synthetic research interns
🚢
DevOps Automation
hollycummins.com
·
6d
6 days ago
Six and a half ridiculous things to do with Quarkus
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Six and a half ridiculous things to do with Quarkus
🌍
Civilizational Risk
lesswrong.com
·
2d
2 days ago
Thoughts on Likelihood of Existential Risks by Misaligned AIs
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Thoughts on Likelihood of Existential Risks by Misaligned AIs
🧠
LLM Training
GitHub
·
4d
4 days ago
Rust port of transformers (1M lines of code)
Discussed on
Hacker News
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Rust port of transformers (1M lines of code)
💻
Tech News
The Blog of Author Tim Ferriss
·
4d
4 days ago
Sebastian Mallaby, Biographer of Demis Hassabis — Lessons from 100+
AI
Insiders on The Race to Superintelligence, The Religion of
AI
, and Spotting Breakthroughs...
Covers
19 stories
See all stories this covers
including
Claude Fable 5 and Claude Mythos 5
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Sebastian Mallaby, Biographer of Demis Hassabis — Lessons from 100+ AI Insiders on The Race to Superintelligence, The Religion of AI, and Spotting Breakthroughs...
🥗
Nutrition
lesswrong.com
·
6d
6 days ago
VFUSE: Virulent Feature Understanding With Sparse AutoEncoders
Covers
Golden Gate Claude
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for VFUSE: Virulent Feature Understanding With Sparse AutoEncoders
🤖
AI
lesswrong.com
·
6d
6 days ago
How Matryoshka Sparse AutoEncoders Recover Feature Hierarchies That Vanilla SAEs Lose
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for How Matryoshka Sparse AutoEncoders Recover Feature Hierarchies That Vanilla SAEs Lose
⚖️
AI Regulation
lesswrong.com
·
5d
5 days ago
Tactical and Operational Exploratory
Modeling
for
AI
Governance
Covers
AI 2027
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Tactical and Operational Exploratory Modeling for AI Governance
🤖
AI
lesswrong.com
·
5d
5 days ago
What are some angles of attack for making continual
learning
safer
?
Covers
2 stories
See all stories this covers
including
Claude's Constitution
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for What are some angles of attack for making continual learning safer?
🔓
Open Source AI
Import AI (Jack Clark)
·
6d
6 days ago
Import
AI
461: "
Alignment
is not on track"; FrontierCode; and synthetic
research
interns
Covers
2 stories
See all stories this covers
including
Introducing FrontierCode
Discussed on
Substack
Love
Like
Not for me
Save
Add to your feed
Feeds
Share
Report
Off Topic
Harmful Content
Low Quality
Spam
Misleading
Duplicate
Wrong Language
Block Domain
Actions for Import AI 461: "Alignment is not on track"; FrontierCode; and synthetic research interns
Log in to enable infinite scrolling
Keyboard Shortcuts
Navigation
Next / previous post
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
Discover
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
Like
Save
Not for me
Report