Skip to main content
Scour
Browse
Getting Started
Login
Sign Up
You are offline. Trying to reconnect...
Copied to clipboard
Unable to share or copy to clipboard
AI Safety
🛡️ AI Safety
AI alignment, AI safety, interpretability, AGI risk, RLHF
Filter Results
Timeframe
Fresh
Past Hour
Today
This Week
This Month
Feeds to Scour
Subscribed
All
Scoured
292
posts in
7.2
ms
Sixteen schemes for
AI
safety
🌲
LSM Trees
lesswrong.com
·
6d
6 days ago
Actions for Sixteen schemes for AI safety
Advanced
AI
Safety
Addendum
🔌
API Design
cloud.google.com
·
17h
17 hours ago
·
Hacker News
Actions for Advanced AI Safety Addendum
The Neutral Mask: How
RLHF
Provides Shallow
Alignment
while Leaving Partisan Structure Intact in a Large Language
Model
🔬
Mech Interp
Content type:
Academic
arxiv.org
·
1d
1 day ago
Actions for The Neutral Mask: How RLHF Provides Shallow Alignment while Leaving Partisan Structure Intact in a Large Language Model
AI
red
teaming
comes of age
🌐
Distributed Systems
csoonline.com
·
4h
4 hours ago
Actions for AI red teaming comes of age
My Oslo Freedom Forum Keynote: Authoritarians and
AI
📊
Observability
Content type:
Blog
redpacket.substack.com
·
1d
1 day ago
·
Substack
Actions for My Oslo Freedom Forum Keynote: Authoritarians and AI
Matador-og/huntbot:
AI
offensive security harness for bug bounty, pentesting,
red
teaming
.
✅
Formal Verification
Content type:
Code
github.com
·
7h
7 hours ago
·
Hacker News
Actions for Matador-og/huntbot: AI offensive security harness for bug bounty, pentesting, red teaming.
Autonomous Pentesting vs Autonomous
Red
Teaming
: What's the Difference?
🌐
Distributed Systems
malware.news
·
3d
3 days ago
Actions for Autonomous Pentesting vs Autonomous Red Teaming: What's the Difference?
[Recorded talk] "
AI
Alignment
Versus
AI
Ethical Treatment: 10 Challenges"
✅
Formal Verification
Content type:
Blog
meditationsondigitalminds.substack.com
·
1d
1 day ago
·
Substack
Actions for [Recorded talk] "AI Alignment Versus AI Ethical Treatment: 10 Challenges"
Claude Fable 5 and new
AI
safety
fables
🌐
Distributed Systems
Content type:
News
interconnects.ai
·
14h
14 hours ago
·
Hacker News
Actions for Claude Fable 5 and new AI safety fables
Mechanistic
Interpretability
: The Key to Trusting Agentic
AI
🔍
Interpretability
Content type:
Discussion
bradenkelley.com
·
4d
4 days ago
Actions for Mechanistic Interpretability: The Key to Trusting Agentic AI
Germany to create
AI
safety
agency
🎲
Procedural Generation
techxplore.com
·
1d
1 day ago
Actions for Germany to create AI safety agency
AI
giant says its own
models
could soon improve themselves — and now it wants a global pause
🔍
Interpretability
thecooldown.com
·
28m
28 minutes ago
Actions for AI giant says its own models could soon improve themselves — and now it wants a global pause
The Best Politician In A Generation
🗂️
Personal Wikis
Content type:
News
Content type:
Blog
benthams.substack.com
·
20h
20 hours ago
·
Substack
Actions for The Best Politician In A Generation
AI
policy
scholar Dean W. Ball
shares
a text from his mother recommending he focus on frontier
AI
policy
🐧
Operating Systems
digg.com
·
6d
6 days ago
Actions for AI policy scholar Dean W. Ball shares a text from his mother recommending he focus on frontier AI policy
Assessing the Polyglot Chatbot: Multilingual
Safety
in
AI
Systems
✅
Formal Verification
cdt.org
·
16h
16 hours ago
Actions for Assessing the Polyglot Chatbot: Multilingual Safety in AI Systems
The Stoic Path to Actual
AI
Safety
: Three Practical Steps for Industry and Individuals
🌐
Distributed Systems
oodaloop.com
·
1d
1 day ago
Actions for The Stoic Path to Actual AI Safety: Three Practical Steps for Industry and Individuals
From oversight to coercion: How authoritarian governments are twisting
AI
safety
to get tech companies to fall in line
🔍
Interpretability
theconversation.com
·
6d
6 days ago
Actions for From oversight to coercion: How authoritarian governments are twisting AI safety to get tech companies to fall in line
Criti-hyping is the best thing that happened to Big Tech
🌐
Distributed Systems
reveriesofahuman.com
·
1d
1 day ago
Actions for Criti-hyping is the best thing that happened to Big Tech
Hidden Consensus:Preference-Validity Compression in Human Feedback
🌐
Distributed Systems
Content type:
Academic
arxiv.org
·
9h
9 hours ago
Actions for Hidden Consensus:Preference-Validity Compression in Human Feedback
OpenAI says it will comply with Trump's order to let the government review
AI
models
before release
✅
Formal Verification
qz.com
·
5d
5 days ago
Actions for OpenAI says it will comply with Trump's order to let the government review AI models before release
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