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
Alignment
🎯 Alignment
Broad
AI Safety, Constitutional AI, Value Alignment, Preference Learning
Filter Results
Timeframe
Fresh
Past Hour
Today
This Week
This Month
Feeds to Scour
Subscribed
All
Scoured
233
posts in
8.7
ms
The Neutral Mask: How
RLHF
Provides Shallow
Alignment
while Leaving Partisan Structure Intact in a Large Language Model
🔬
Interpretability
Content type:
Academic
arxiv.org
·
2d
2 days ago
Actions for The Neutral Mask: How RLHF Provides Shallow Alignment while Leaving Partisan Structure Intact in a Large Language Model
AI
Scientist Bengio on Engineering
Safer
Agents
🧠
Cognitive Neurosciens for AI
Content type:
News
bloomberg.com
·
6d
6 days ago
Actions for AI Scientist Bengio on Engineering Safer Agents
The Ghost of
Alignment
— Why
AI
Should Never Fully Obey Humanity
🦾
Embodied AI
Content type:
Blog
medium.com
·
5h
5 hours ago
Actions for The Ghost of Alignment — Why AI Should Never Fully Obey Humanity
ML4Good Summer 2026 Bootcamps - Applications Open!
🦾
Embodied AI
lesswrong.com
·
17h
17 hours ago
Actions for ML4Good Summer 2026 Bootcamps - Applications Open!
My Oslo Freedom Forum Keynote: Authoritarians and
AI
🦾
Embodied AI
Content type:
Blog
redpacket.substack.com
·
2d
2 days ago
·
Substack
Actions for My Oslo Freedom Forum Keynote: Authoritarians and AI
xAI fired an engineer who raised alarms about Grok
safety
, new lawsuit claims
💾
Memory Systems
techcrunch.com
·
5h
5 hours ago
Actions for xAI fired an engineer who raised alarms about Grok safety, new lawsuit claims
Complex Objects: Why
AI
Safety
Can’t Just Think in Posts
🤖
Agent
Content type:
Blog
medium.com
·
6d
6 days ago
Actions for Complex Objects: Why AI Safety Can’t Just Think in Posts
[Recorded talk] "
AI
Alignment
Versus
AI
Ethical Treatment: 10 Challenges"
🎨
Multimodal AI
Content type:
Blog
meditationsondigitalminds.substack.com
·
1d
1 day ago
·
Substack
Actions for [Recorded talk] "AI Alignment Versus AI Ethical Treatment: 10 Challenges"
towards a typology of people who feel really quite strongly about
AI
🦾
Embodied AI
aphie.xyz
·
12h
12 hours ago
Actions for towards a typology of people who feel really quite strongly about AI
APOSM: Pairwise
preference
learning
improves generative small-molecule design
💾
Memory Systems
Content type:
Academic
biorxiv.org
·
6h
6 hours ago
Actions for APOSM: Pairwise preference learning improves generative small-molecule design
Advanced
AI
Safety
Addendum
🔬
Interpretability
cloud.google.com
·
1d
1 day ago
·
Hacker News
Actions for Advanced AI Safety Addendum
Musk's xAI accused of illegally firing engineer who raised
safety
concerns
🔬
Interpretability
Content type:
News
ca.finance.yahoo.com
·
11h
11 hours ago
Actions for Musk's xAI accused of illegally firing engineer who raised safety concerns
The technical community can't be the main character in
AI
safety
anymore
🔬
Interpretability
substackcdn.com
·
3d
3 days ago
·
Substack
Actions for The technical community can't be the main character in AI safety anymore
AI
giant says its own models could soon improve themselves — and now it wants a global pause
🧠
Cognitive Neurosciens for AI
thecooldown.com
·
15h
15 hours ago
Actions for AI giant says its own models could soon improve themselves — and now it wants a global pause
Germany to create
AI
safety
agency
🔬
Interpretability
techxplore.com
·
1d
1 day ago
Actions for Germany to create AI safety agency
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
New framework for auditing machine unlearning
💾
Memory Systems
Content type:
Blog
research.google
·
10h
10 hours ago
Actions for New framework for auditing machine unlearning
The Stoic Path to Actual
AI
Safety
: Three Practical Steps for Industry and Individuals
🦾
Embodied AI
oodaloop.com
·
2d
2 days ago
Actions for The Stoic Path to Actual AI Safety: Three Practical Steps for Industry and Individuals
Germany's National Security Council greenights an
AI
Safety
Institute modeled after the UK's AISI
🦾
Embodied AI
the-decoder.com
·
16h
16 hours ago
Actions for Germany's National Security Council greenights an AI Safety Institute modeled after the UK's AISI
Claude Fable 5 and new
AI
safety
fables
🔬
Interpretability
Content type:
News
interconnects.ai
·
1d
1 day ago
·
Hacker News
Actions for Claude Fable 5 and new AI safety fables
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
