AI Safety

Feeds to Scour
SubscribedAll
Scoured 62 posts in 6.1 ms

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

 🧠Philosophy  Content type: Blog

Mechanistic Interpretability: The Key to Trusting Agentic AI

 🤖LLMs  Content type: Discussion
bradenkelley.com·

The Ghost of Alignment — Why AI Should Never Fully Obey Humanity

 🔄Transformers  Content type: Blog
medium.com
·

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

 🌐Trade Policy
lesswrong.com·

Trajectory Geometry of Transformer Representations Across Layers

 🔄Transformers  Content type: Academic
arxiv.org·

From oversight to coercion: How authoritarian governments are twisting AI safety to get tech companies to fall in line

 📜Tech Policy
theconversation.com·

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

 💻Tech News

Controversial smut as an AI alignment issue

 📚Literature  Content type: News  Content type: Blog

Solsong Chord Updates

 🎵Music
jefftk.com·

Anthropic’s Shocking Warning: AI Could Soon Upgrade Itself—Should the World Hit Pause?

 🔄Transformers  Content type: Video
youtube.com·

Mathematical proof reveals why fixed AI guardrails can never block every jailbreak

 🤖AI
techxplore.com·

VFUSE: Virulent Feature Understanding with Sparse autoEncoders

 👁️Computer Vision  Content type: Academic
arxiv.org·

Op Ed: Consultant Tony O’Connor On The Agentic Trojan Horse

 📜Tech Policy
thecompanydime.com·

The crucial human component in computing and AI

 👁️Computer Vision  Content type: Academic
news.mit.edu·

Designer babies. Self-improving AI. Are we ready for either?

 🔬Science  Content type: News
vox.com
·

OpenClaw Won: How Big Tech Adopted the AI Agent

 🚀Startups
thelettertwo.com·

Why Claude Produces High-Quality Output: A Developer’s Guide to Token Efficiency and Hallucination…

 🤖LLMs  Content type: Blog
medium.com·
Less-relevant results

Is the Space Pope Reptilian?

 🤖AI  Content type: News
tearsinrain.ai··Hacker News

Neglected Basics of AI Alignment

 🎮Reinforcement Learning
lesswrong.com·

A free diagnostic for the Claude Certified Architect exam

 🤖AI  Content type: Discussion  Content type: Tutorial

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