Skip to main content
Scour
Browse
Getting Started
Login
Sign Up
You are offline. Trying to reconnect...
Copied to clipboard
Unable to share or copy to clipboard
AI Safety
🛡️ AI Safety
Alignment, Interpretability, Adversarial Examples, Ethics
Filter Results
Timeframe
Fresh
Past Hour
Today
This Week
This Month
Feeds to Scour
Subscribed
All
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
·
2d
2 days ago
Actions for Position: Don't Just "Fix it in Post": A Science of AI Must Study Training Dynamics
Installing the Seat on the
Machine
📜
Tech Policy
cafebedouin.org
·
6d
6 days ago
Actions for Installing the Seat on the Machine
SecureBio Detection is Hiring Software Engineers
🚀
Startups
jefftk.com
·
5d
5 days ago
Actions for SecureBio Detection is Hiring Software Engineers
Inside the Visual Mind: Neuroscience-Motivated Concept Circuits for
Interpreting
and Steering Vision Transformers
👁️
Computer Vision
Content type:
Academic
arxiv.org
·
2d
2 days ago
Actions for Inside the Visual Mind: Neuroscience-Motivated Concept Circuits for Interpreting and Steering Vision Transformers
One Year of PauseAI UK
🎬
Documentaries
lesswrong.com
·
5d
5 days ago
Actions for One Year of PauseAI UK
Emergent
alignment
and the projectability of
ethical
personas
🔄
Transformers
Content type:
Academic
arxiv.org
·
1d
1 day ago
Actions for Emergent alignment and the projectability of ethical personas
DiffoR: A Unified Continuous Generative Framework for Universal Ordinal Regression
👁️
Computer Vision
Content type:
Academic
arxiv.org
·
1d
1 day ago
Actions for DiffoR: A Unified Continuous Generative Framework for Universal Ordinal Regression
Book of Cron Job
📚
Literature
lesswrong.com
·
6d
6 days ago
Actions for Book of Cron Job
Subspace-Aware Sparse Autoencoders for Effective
Mechanistic
Interpretability
🤖
LLMs
Content type:
Academic
arxiv.org
·
5d
5 days ago
Actions for Subspace-Aware Sparse Autoencoders for Effective Mechanistic Interpretability
Contra Dance at LessOnline
⚖
class politics
jefftk.com
·
3d
3 days ago
Actions for Contra Dance at LessOnline
Wearable
Single-Lead
ECG Detects Fine-Grained Structural Heart Disease Through Echo-Report Supervision
🩺
Health
Content type:
Academic
arxiv.org
·
1d
1 day ago
Actions for Wearable Single-Lead ECG Detects Fine-Grained Structural Heart Disease Through Echo-Report Supervision
Less-relevant results
Towards a Formal Scientific Epistemology
🧠
Philosophy
lesswrong.com
·
1d
1 day ago
Actions for Towards a Formal Scientific Epistemology
Coming Around To Political Donations
⚖
class politics
jefftk.com
·
4d
4 days ago
Actions for Coming Around To Political Donations
How authoritarian governments twist
AI
safety
to coerce tech companies to comply
📜
Tech Policy
fastcompany.com
·
3d
3 days ago
Actions for How authoritarian governments twist AI safety to coerce tech companies to comply
Temporal Preference Concepts and their Functions in a Large Language
Model
🤖
LLMs
Content type:
Academic
arxiv.org
·
5d
5 days ago
Actions for Temporal Preference Concepts and their Functions in a Large Language Model
Towards Evaluating the
Robustness
of Visual State Space
Models
👁️
Computer Vision
Content type:
Academic
arxiv.org
·
6d
6 days ago
Actions for Towards Evaluating the Robustness of Visual State Space Models
PerceptTwin: Semantic Scene Reconstruction for Iterative LLM Planning and Verification
🎮
Reinforcement Learning
Content type:
Academic
arxiv.org
·
6d
6 days ago
Actions for PerceptTwin: Semantic Scene Reconstruction for Iterative LLM Planning and Verification
[Paper] Dictionary
Learning
Identifiability for Understanding SAEs
🤖
AI
lesswrong.com
·
6d
6 days ago
Actions for [Paper] Dictionary Learning Identifiability for Understanding SAEs
Mechanistic
Insights into Functional Sparsity in Multimodal LLMs via CoRe Heads
🤖
LLMs
Content type:
Academic
arxiv.org
·
5d
5 days ago
Actions for Mechanistic Insights into Functional Sparsity in Multimodal LLMs via CoRe Heads
Unsupervised Pattern Analysis in Japanese Veterinary Toxicology: A Regulatory-Compliant Framework for Cross-Species Risk Assessment
👁️
Computer Vision
Content type:
Academic
arxiv.org
·
5d
5 days ago
Actions for Unsupervised Pattern Analysis in Japanese Veterinary Toxicology: A Regulatory-Compliant Framework for Cross-Species Risk Assessment
Sign up or log in to see more results
Sign Up
Login
« Page 2
Log in to enable infinite scrolling
Keyboard Shortcuts
Navigation
Next / previous item
j
/
k
Open post
o
or
Enter
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
g
h
Interests
g
i
Feeds
g
f
Likes
g
l
History
g
y
Changelog
g
c
Settings
g
s
Browse
g
b
Search
/
Pagination
Next page
n
Previous page
p
General
Show this help
?
Submit feedback
!
Close modal / unfocus
Esc
Press
?
anytime to show this help