AI Safety

Feeds to Scour
SubscribedAll
Scoured 76 posts in 5.0 ms

OpenClaw Won: How Big Tech Adopted the AI Agent

 🧭LLM Alignment
thelettertwo.com·

Installing the Seat on the Machine

 🧭LLM Alignment
cafebedouin.org·

Trajectory Geometry of Transformer Representations Across Layers

 🧭LLM Alignment  Content type: Academic
arxiv.org·

Iliad is Hiring

 🧭LLM Alignment
lesswrong.com·

AI, religion and AI religion | Andrew Orlowski

 🧠Rationalism
thecritic.co.uk·

Revisiting the shutdown problem

 🎭AI Simulators  Content type: Academic
arxiv.org·

Coelho Mollo and Millière: The Vector Grounding Problem

 🧭LLM Alignment

Your model provider is now your competitor (4 minute read)

 🦋ATProto  Content type: News  Content type: Blog

Neglected Basics of AI Alignment

 🧭LLM Alignment
lesswrong.com·

Ablation-Reversible Heads Don't Transfer: A Stress Test for Mechanistic Role Claims in Transformers

 🧭LLM Alignment  Content type: Academic
arxiv.org·
Less-relevant results

The $300K Engineer Is Usually Cheaper Than the $80K One

 🧭LLM Alignment
siliconopera.com·

A CEO told employees they won't get raises in 2026 because the budget is going to AI

 🤖AGI

Why Conflict Feels Constant Now

 📝Long-form Essays
noemamag.com·

FoldSAE: Learning to Steer Protein Folding Through Sparse Representations

 🧭LLM Alignment  Content type: Academic
arxiv.org·

Contra Dance at LessOnline

 🧭LLM Alignment
jefftk.com·

Shared Semantics, Divergent Mechanisms: Unsupervised Feature Discovery by Aligning Semantics and Mechanisms

 🧭LLM Alignment  Content type: Academic
arxiv.org·

Adora Magic City Launches China's First Cruise-to-Nowhere from Shanghai, Transforming Domestic Tourism in 2026

 🎭AI Simulators  Content type: News
nomadlawyer.org·

Towards a Formal Scientific Epistemology

 🧠Rationalism
lesswrong.com·

Interactions Between Crosscoder Features: A Compact Proofs Perspective

 🧭LLM Alignment  Content type: Academic
arxiv.org·

The Psychological Challenges of High-Impact Work - please participate in our survey!

 🧩Cognitive Science
lesswrong.com·
Sign up or log in to see more results

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