AI Safety

AI alignment, safety research, interpretability, superintelligence

Feeds to Scour
SubscribedAll
Scoured 140 posts in 6.7 ms

Mechanistic Interpretability: The Key to Trusting Agentic AI

 🔓Open Source AI  Content type: Discussion
bradenkelley.com·

Iliad is Hiring

 🔓Open Source AI
lesswrong.com·

VFUSE: Virulent Feature Understanding with Sparse autoEncoders

 🤖ai  Content type: Academic
arxiv.org·

How CrowdStrike Bets on Security AGI with Bartley Richardson

 🤖ai  Content type: News
aimagazine.com·

[Recorded talk] "AI Alignment Versus AI Ethical Treatment: 10 Challenges"

 🤖ai  Content type: Blog

30+ Canadian MPs and Senators Call for a Ban on Superintelligence

 🤖ai
controlai.news·

Microsoft’s AI chief says superintelligence is near, but won’t take your job

 🤖ai  Content type: Video  Content type: News

AI pioneer Geoffrey Hinton warns of conscious superintelligence and existential risk

 🧠AI Research
4sysops.com·

Statement: Anthropic warns of AI self-improvement risks, considers a pause

 🤖ai
futureoflife.org·

SoftBank's Masayoshi Son says AI is already designing OpenAI's next model

 🤖ai
qz.com·

Criti-hyping is the best thing that happened to Big Tech

 Software Perf

When Attribution Patching Lies: Diagnosis and a Second-Order Correction

 🧠AI Research  Content type: Academic
arxiv.org·

Microsoft AI chief says company was “set free” from OpenAI to pursue superintelligence

 🤖ai
venturebeat.com·

Microsoft’s AI Chief Insists He’s Not Posting Thirst Traps on Main After Messy Breakup With OpenAI

 🤖ai
gizmodo.com·

Microsoft just shared the frontier data engineering secrets

 🤖ai
mail.bycloud.ai·

The Three Filters: Why Almost Every Plan to Survive ASI Fails Miserably

 🤖ai
lesswrong.com·

Controversial smut as an AI alignment issue

 🤖ai  Content type: News  Content type: Blog

Mira Murati Unveils Her Startup’s A.I. Model in First Interview Since OpenAI

 🔓Open Source AI  Content type: News
observer.com·

Some economics of artificial superintelligence

 🤖ai  Content type: Academic
arxiv.org·

Microsoft swears its OpenAI breakup isn’t a messy divorce.

 🤖ai  Content type: News
theverge.com·

Keyboard Shortcuts

Navigation

Next / previous item
j/k
Open post
oorEnter
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
gh
Interests
gi
Feeds
gf
Likes
gl
History
gy
Changelog
gc
Settings
gs
Browse
gb
Search
/

General

Show this help
?
Submit feedback
!
Close modal / unfocus
Esc

Press ? anytime to show this help