curius graph

all pages

showing 78651-78700 of 203025 pages (sorted by popularity)
Fluent dreaming for language models
Gemma 2: Improving Open Language Models at a Practical Size
Do Large Language Model Benchmarks Test Reliability? – gradient science
How do we solve the alignment problem?
AI Futures Project | Artificial Intelligence Forecasting, Inc., DBA AI Futures Project is a 501(c)3 nonprofit research organization. We are funded entirely by charitable donations and grants.
Chain of Continuous Thoughts | Ben Congdon
cookbook/examples/prompting/Chain_of_thought_prompting.ipynb at main · google-gemini/cookbook
[2501.17148] AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders
[2405.18915] Towards Faithful Chain-of-Thought: Large Language Models are Bridging Reasoners
Towards Faithful Chain-of-Thought: Large Language Models are Bridging Reasoners
[2310.18512] Preventing Language Models From Hiding Their Reasoning
18022025 Mary Meeting Agenda - Google Docs
Being Present is Not a Skill - by Chris Lakin
[2309.16797] Promptbreeder: Self-Referential Self-Improvement via Prompt Evolution
A minimal viable product for alignment - by Jan Leike
[2312.06942] AI Control: Improving Safety Despite Intentional Subversion
[2310.00492] From Language Modeling to Instruction Following: Understanding the Behavior Shift in LLMs after Instruction Tuning
[2403.10415] Gradient based Feature Attribution in Explainable AI: A Technical Review
[2405.18915] Towards Faithful Chain-of-Thought: Large Language Models are Bridging Reasoners
kenny-evitt/ynas: You Need A Schedule
Suchir Balaji
[2409.14507] A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders
A Proven Way to Ease L.A.’s Housing Crisis - The Atlantic
[2410.06992] SWE-Bench+: Enhanced Coding Benchmark for LLMs
[2406.10209] Be like a Goldfish, Don’t Memorize! Mitigating Memorization in Generative LLMs
Catching AIs red-handed — AI Alignment Forum
[1606.03137] Cooperative Inverse Reinforcement Learning
ja3k.com Archive
[2502.09992] Large Language Diffusion Models
A central AI alignment problem: capabilities generalization, and the sharp left turn — LessWrong
Reflection: A Path to Superintelligence - Reflection AI
[2502.04040] Leveraging Reasoning with Guidelines to Elicit and Utilize Knowledge for Enhancing Safety Alignment
[2502.19402] General Reasoning Requires Learning to Reason from the Get-go
AIs Will Increasingly Attempt Shenanigans — LessWrong
AI Control: The Great Cold War
Proof-of-Concept Debugger for a Small LLM — LessWrong
[2411.00986] Taking AI Welfare Seriously
[2405.14860] Not All Language Model Features Are Linear
Going Nova - by Zvi Mowshowitz - Don't Worry About the Vase
kalomaze's kalomazing blog
Ghostty Config - Window
The End of the Observer Problem: How the Universe Computes Itself into Existence
How To Believe False Things - by Eneasz Brodski
First Chakra: Mooladhara Chakra
AI #107: The Misplaced Hype Machine - by Zvi Mowshowitz
On (Not) Feeling the AGI — LessWrong
Emptiness in the Aro gTér | Vividness
The Benefits of Standing Meditation - Tasshin
Why White-Box Redteaming Makes Me Feel Weird — LessWrong
What even is Focusing and why Eugene Gendlin is the greatest man to ever grace the Earth with his existence