AI Safety

Feeds to Scour
SubscribedAll
Scoured 61 posts in 7.2 ms

OpenClaw Won: How Big Tech Adopted the AI Agent

 🤝AI Agents
thelettertwo.com·

Iliad is Hiring

 🏗️Platform Engineering
lesswrong.com·

scMTG reconstructs single-cell temporal dynamics with Markov transition generators

 🧠LLMs  Content type: Academic
biorxiv.org·

Order Is Not Control

 🕸️Distributed Systems  Content type: Academic
arxiv.org·

Sequent: scale and automation for higher confidence in alignment

 🧠LLMs
lesswrong.com·
Less-relevant results

A free diagnostic for the Claude Certified Architect exam

 🤝AI Agents  Content type: Discussion  Content type: Tutorial

Contra Dance at LessOnline

 🕸️Distributed Systems

Complete Drosophila Nervous System Mapped

 🕸️Distributed Systems
neurosciencenews.com·

Bag of Dims: Training-Free Mechanistic Interpretability via Dimension-Level Sign Patterns

 🧠LLMs  Content type: Academic
arxiv.org·

Announcing the Next Phase of AI Forge

 🤖AI Engineering
lesswrong.com·

Existential Indifference: Self-Nonpreservation as a Necessary Architectural Condition for Aligned Superintelligence (or: The Suicidal AI)

 🤝AI Agents  Content type: Academic
arxiv.org·

Construct validity of Claude Opus 4.8's System Card – A commentary

 🤝AI Agents
lesswrong.com·

Coming Around To Political Donations

 🧠LLMs

Eigenism: Ethics for a Human-AI Future

 🕸️Distributed Systems  Content type: Academic
arxiv.org·

Superspace Concentration and Adversarial Robustness in Quantum Algorithms

 🕸️Distributed Systems  Content type: Academic
arxiv.org·

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

 🧠LLMs  Content type: Academic
arxiv.org·

High Dynamic Range DIY Air Testing

 🕸️Distributed Systems

RogueAI: A Reverse Turing Test for Detecting Licensed AI Deception in Dialogue

 🧠LLMs  Content type: Academic
arxiv.org·

Layer-Resolved Optimal Transport for Hallucination Detection in NMT and Abstractive Summarization

 🧠LLMs  Content type: Academic
arxiv.org·

The Standard Interpretable Model: A general theory of interpretable machine learning to deductively design interpretable methods using Lagrangian mechanics

 🧠LLMs  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