curius graph

all pages

showing 145251-145300 of 200407 pages (sorted by popularity)
Ordinal number - Wikipedia
Zen - Wikipedia
60 kHz
Shard Theory - AI Alignment Forum
[1706.03741] Deep reinforcement learning from human preferences
Looking back on my alignment PhD
AI Ruined My Year - YouTube
My relationship with digital media in the last few years
Many arguments for AI x-risk are wrong
Many arguments for AI x-risk are wrong — LessWrong
This message does not exist | Mark J. Nelson
githublog/2024/5/29/fast-inverse-sqrt.md at main · francisrstokes/githublog
How it feels to get an AI email from a friend
How it All Went Down: The Puzzle Hunt that took us way, way Less Online — LessWrong
I'm forking Ladybird and stepping down as SerenityOS BDFL
About
rapid psychological growth - Chris Lakin’s blog
About Cody Rushing
[Paper] Stress-testing capability elicitation with password-locked models — LessWrong
Memorizing weak examples can elicit strong behavior out of password-locked models — LessWrong
Speeding up and reducing memory usage for scientific machine learning via mixed precision - ScienceDirect
Appendix: Is there a simple algorithm for intelligence?
Psychological issues are often useful in the present
Relationship between diet and ankylosing spondylitis: A systematic review - PubMed
Shtetl-Optimized » Blog Archive » Situational Awareness
[2209.14905] Variance Covariance Regularization Enforces Pairwise Independence in Self-Supervised Representations
Long-Term Future Fund: March 2024 Payout recommendations — LessWrong
toy-models-of-superposition/toy_models.ipynb at main · anthropics/toy-models-of-superposition
updates | MIT Admissions
Paris Hilton's Ghostwritten Memoir
Manifesting Manifest - Rachel’s Substack
Toy Models of Superposition
Francois Chollet - LLMs won’t lead to AGI - $1,000,000 Prize to find true solution - YouTube
About my writing | Meaningness
Getting 50% (SoTA) on ARC-AGI with GPT-4o — LessWrong
The Singular Value Decompositions of Transformer Weight Matrices are Highly Interpretable — LessWrong
What’s up with LLMs representing XORs of arbitrary features? — LessWrong
dnhkng/PCAonGPU: A GPU-based Incremental PCA implementation.
[2310.08043] Understanding and Controlling a Maze-Solving Policy Network
Social interaction-inspired AI alignment
Neural Networks, Manifolds, and Topology -- colah's blog
Free State Project - Wikipedia
The Minority Faction - by Richard Ngo - Narrative Ark
llama2.c/model.py at 350e04fe35433e6d2941dce5a1f53308f87058eb · karpathy/llama2.c
Empirical vs. Mathematical Joints of Nature — LessWrong
roneneldan/TinyStories-33M · Hugging Face
How Big a Deal are MatMul-Free Transformers? — LessWrong
How my day is going - by Sasha Chapin
My 2024 Presidential Debate - by Scott Alexander
Synergy Greg — Ludicity