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 risk, existential risk, AGI safety
Filter Results
Timeframe
Fresh
Past Hour
Today
This Week
This Month
Feeds to Scour
Subscribed
All
Scoured
243
posts in
7.2
ms
Mechanistic
Interpretability
: The Key to Trusting Agentic
AI
🔍
Cognitive Bias
Content type:
Discussion
bradenkelley.com
·
4d
4 days ago
Actions for Mechanistic Interpretability: The Key to Trusting Agentic AI
Advanced
AI
Safety
Addendum
💻
Tech Journalism
cloud.google.com
·
1d
1 day ago
·
Hacker News
Actions for Advanced AI Safety Addendum
ML4Good Summer 2026 Bootcamps - Applications Open!
💡
Effective Altruism
lesswrong.com
·
11h
11 hours ago
Actions for ML4Good Summer 2026 Bootcamps - Applications Open!
Musk's xAI accused of illegally firing engineer who raised
safety
concerns
💻
Tech Journalism
Content type:
News
ca.finance.yahoo.com
·
5h
5 hours ago
Actions for Musk's xAI accused of illegally firing engineer who raised safety concerns
My Oslo Freedom Forum Keynote: Authoritarians and
AI
🗳️
Liberal Democracy
Content type:
Blog
redpacket.substack.com
·
1d
1 day ago
·
Substack
Actions for My Oslo Freedom Forum Keynote: Authoritarians and AI
VFUSE: Virulent Feature Understanding with Sparse autoEncoders
💻
Tech Journalism
Content type:
Academic
arxiv.org
·
18h
18 hours ago
Actions for VFUSE: Virulent Feature Understanding with Sparse autoEncoders
The technical community can't be the main character in
AI
safety
anymore
⚖️
Political Economy
substackcdn.com
·
3d
3 days ago
·
Substack
Actions for The technical community can't be the main character in AI safety anymore
Reward
Hacking
, The Loophole Lesson: Winning the Signal, Losing the Reason
🔍
Cognitive Bias
Content type:
Blog
medium.com
·
2d
2 days ago
Actions for Reward Hacking, The Loophole Lesson: Winning the Signal, Losing the Reason
Claude Fable 5 and new
AI
safety
fables
🔍
Cognitive Bias
Content type:
News
interconnects.ai
·
23h
23 hours ago
·
Hacker News
Actions for Claude Fable 5 and new AI safety fables
[Recorded talk] "
AI
Alignment
Versus
AI
Ethical Treatment: 10 Challenges"
🔍
Cognitive Bias
Content type:
Blog
meditationsondigitalminds.substack.com
·
1d
1 day ago
·
Substack
Actions for [Recorded talk] "AI Alignment Versus AI Ethical Treatment: 10 Challenges"
OpenAI says it will comply with Trump's order to let the government review
AI
models before release
💻
Tech Journalism
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
AI
giant says its own models could soon improve themselves — and now it wants a global pause
🔍
Cognitive Bias
thecooldown.com
·
9h
9 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
🔍
Cognitive Bias
techxplore.com
·
1d
1 day ago
Actions for Germany to create AI safety agency
AI
Scientist Bengio on Engineering
Safer
Agents
🔍
Cognitive Bias
Content type:
News
bloomberg.com
·
6d
6 days ago
Actions for AI Scientist Bengio on Engineering Safer Agents
towards a typology of people who feel really quite strongly about
AI
✊
Populism
aphie.xyz
·
7h
7 hours ago
Actions for towards a typology of people who feel really quite strongly about AI
Import
AI
460:
Reward
hacking
society, RSI data from Anthropic; and RL-based quadcopter racing
💡
Effective Altruism
Content type:
News
Content type:
Blog
importai.substack.com
·
2d
2 days ago
·
Substack
Actions for Import AI 460: Reward hacking society, RSI data from Anthropic; and RL-based quadcopter racing
Anthropic releases Mythos-derived model with cyber guardrails
🔍
Cognitive Bias
metacurity.com
·
8h
8 hours ago
Actions for Anthropic releases Mythos-derived model with cyber guardrails
From oversight to coercion: How authoritarian governments are twisting
AI
safety
to get tech companies to fall in line
🔍
Cognitive Bias
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
The Stoic Path to Actual
AI
Safety
: Three Practical Steps for Industry and Individuals
🔍
Cognitive Bias
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
🔍
Cognitive Bias
the-decoder.com
·
10h
10 hours ago
Actions for Germany's National Security Council greenights an AI Safety Institute modeled after the UK's AISI
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
