AI Safety

Feeds to Scour
SubscribedAll
Scoured 74 posts in 4.3 ms

FoldSAE: Learning to Steer Protein Folding Through Sparse Representations

 🧠LLMs  Content type: Academic
arxiv.org·

Epiplexity

 🤖AI Agents  Content type: Blog
andys.blog··Hacker News

‘We Did Our Best!’ | Meghan O’Gieblyn

 ✍️Prompt Engineering
nybooks.com·

Principled Agent Debate: Adversarial Arbitration for Sycophancy Reduction in Large Language Models

 🧠LLMs  Content type: Academic
arxiv.org·

Book of Cron Job

 ✍️Prompt Engineering
lesswrong.com·

What Do People Actually Want From AI? Mapping Preference Plurality

 🧠LLMs  Content type: Academic
arxiv.org·

Contra Dance at LessOnline

 🔷Ethereum
jefftk.com·

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

 ✍️Prompt Engineering  Content type: Academic
arxiv.org·

The Shibboleth Effect: Auditing the Cross-Lingual Distributional Skew of Large Language Models

 🧠LLMs  Content type: Academic
arxiv.org·

Installing the Seat on the Machine

 ✍️Prompt Engineering
cafebedouin.org·

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

 ✍️Prompt Engineering  Content type: Academic
arxiv.org·

My research agenda and work

 🧠LLMs
lesswrong.com·

(VERY PARTIAL) CROSSPOST: ALEX HEATH: SubStack Is Opening Up to AI: Interviewing CEO Chris Best

 🧠LLMs  Content type: News  Content type: Blog

Interactions Between Crosscoder Features: A Compact Proofs Perspective

 🧠LLMs  Content type: Academic
arxiv.org·

Towards a Formal Scientific Epistemology

 🤖AI Agents
lesswrong.com·

EvalStop: Using World Feedback to Detect and Correct Reward Overoptimization in Multi-Tenant RLHF Platforms

 🧠LLMs  Content type: Academic
arxiv.org·

Coming Around To Political Donations

 💰Long-Term Investing
jefftk.com·

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

 🤖AI Agents  Content type: Academic
arxiv.org·

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

 🧠LLMs  Content type: Academic
arxiv.org·

Subspace-Aware Sparse Autoencoders for Effective Mechanistic Interpretability

 🧠LLMs  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