AI Safety

Feeds to Scour
SubscribedAll
Scoured 61 posts in 5.4 ms

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

 🤖AI  Content type: Academic
arxiv.org·

Installing the Seat on the Machine

 📜Tech Policy
cafebedouin.org·

SecureBio Detection is Hiring Software Engineers

 🚀Startups
jefftk.com·

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

 👁️Computer Vision  Content type: Academic
arxiv.org·

One Year of PauseAI UK

 🎬Documentaries
lesswrong.com·

Emergent alignment and the projectability of ethical personas

 🔄Transformers  Content type: Academic
arxiv.org·

DiffoR: A Unified Continuous Generative Framework for Universal Ordinal Regression

 👁️Computer Vision  Content type: Academic
arxiv.org·

Book of Cron Job

 📚Literature
lesswrong.com·

Subspace-Aware Sparse Autoencoders for Effective Mechanistic Interpretability

 🤖LLMs  Content type: Academic
arxiv.org·

Contra Dance at LessOnline

 class politics
jefftk.com·

Wearable Single-Lead ECG Detects Fine-Grained Structural Heart Disease Through Echo-Report Supervision

 🩺Health  Content type: Academic
arxiv.org·
Less-relevant results

Towards a Formal Scientific Epistemology

 🧠Philosophy
lesswrong.com·

Coming Around To Political Donations

 class politics
jefftk.com·

How authoritarian governments twist AI safety to coerce tech companies to comply

 📜Tech Policy
fastcompany.com·

Temporal Preference Concepts and their Functions in a Large Language Model

 🤖LLMs  Content type: Academic
arxiv.org·

Towards Evaluating the Robustness of Visual State Space Models

 👁️Computer Vision  Content type: Academic
arxiv.org·

PerceptTwin: Semantic Scene Reconstruction for Iterative LLM Planning and Verification

 🎮Reinforcement Learning  Content type: Academic
arxiv.org·

[Paper] Dictionary Learning Identifiability for Understanding SAEs

 🤖AI
lesswrong.com·

Mechanistic Insights into Functional Sparsity in Multimodal LLMs via CoRe Heads

 🤖LLMs  Content type: Academic
arxiv.org·

Unsupervised Pattern Analysis in Japanese Veterinary Toxicology: A Regulatory-Compliant Framework for Cross-Species Risk Assessment

 👁️Computer Vision  Content type: Academic
arxiv.org·
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