Anthropic PBC

Feeds to Scour
SubscribedAll
Scoured 27 posts in 10.7 ms

Anthropic Calls for AI Pause Button to Let Humans Take Stock

 🎭Claude  Content type: News
bloomberg.com
··Hacker News
Less-relevant results

Trajectory Geometry of Transformer Representations Across Layers

 🔍AI Interpretability  Content type: Academic
arxiv.org·

SoftBank Attempt to Get $6 Billion OpenAI Margin Loan Stalls

 🎭Claude  Content type: News
finance.yahoo.com··Hacker News

Anthropic warns Claude AI is building itself faster than expected, calls for option to halt frontier development — 'recursive self improvement' increases risk humans lose control of AI

 🎭Claude  Content type: News
tomshardware.com
··Hacker News

A free diagnostic for the Claude Certified Architect exam

 🔌Claude Plugins  Content type: Discussion  Content type: Tutorial
claudecertifiedarchitects.com··Hacker News

Anthropic calls for global pause in AI development before humans lose control

 🎭Claude
siliconangle.com··Hacker News

nanxstats/anthrosevka: An Iosevka custom build inspired by Anthropic Mono

 🎭Claude  Content type: Code
github.com··Hacker News

VFUSE: Virulent Feature Understanding with Sparse autoEncoders

 🔍AI Interpretability  Content type: Academic
arxiv.org·

Position: Don't Just "Fix it in Post": A Science of AI Must Study Training Dynamics

 🔍AI Interpretability  Content type: Academic
arxiv.org·

The OnlyFans Economy of American AI

 🤖AI  Content type: Blog
leoveanu.com··Hacker News

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

 🔍AI Interpretability  Content type: Academic
arxiv.org·

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

 🔍AI Interpretability  Content type: Academic
arxiv.org·

How much AI is too much?

 🎭Claude
irishtimes.com··Hacker News

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

 🔍AI Interpretability  Content type: Academic
arxiv.org·

Is the Space Pope Reptilian?

 🎯Alignment Research  Content type: News
tearsinrain.ai··Hacker News

Airbnb CEO Brian Chesky Plans to Start a New AI Company

 🎭Claude
finance.yahoo.com··Hacker News

Interactions Between Crosscoder Features: A Compact Proofs Perspective

 🔍AI Interpretability  Content type: Academic
arxiv.org·

Automating Myself Out of Development – Part2

 🎭Claude  Content type: News
thoughtfultechnologist.com··Hacker News

Subspace-Aware Sparse Autoencoders for Effective Mechanistic Interpretability

 🔍AI Interpretability  Content type: Academic
arxiv.org·

Inside the Visual Mind: Neuroscience-Motivated Concept Circuits for Interpreting and Steering Vision Transformers

 🔍AI Interpretability  Content type: Academic
arxiv.org·

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