curius graph

all pages

showing 151001-151050 of 200407 pages (sorted by popularity)
[2503.03750] The MASK Benchmark: Disentangling Honesty From Accuracy in AI Systems
[2407.21792] Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?
Stephen Fitz
anthropics/evals
evals/advanced-ai-risk at main · anthropics/evals
[2304.03279] Do the Rewards Justify the Means? Measuring Trade-Offs Between Rewards and Ethical Behavior in the MACHIAVELLI Benchmark
LMSYS Org
[2008.02275] Aligning AI With Shared Human Values
A starter guide for evals — LessWrong
2410.24190
Persona Vectors: Monitoring and Controlling Character Traits in Language Models
22-Science-Diplomacy-TR.pdf
Introduction to ChoiceScript - Choice of Games LLC
Ed.blog
Is San Francisco “back”? I audited its parties to find out – Ed.blog
AI & Science Reading Group
‪Francois Charton‬ - ‪Google Scholar‬
[2502.17513] Int2Int: a framework for mathematics with transformers
2112.01898
Machine Learning: The High Interest Credit Card of Technical Debt
43146.pdf
Tesseract - Wikipedia
Charles Howard Hinton - Wikipedia
The unreasonable effectiveness of deep learning in artificial intelligence | PNAS
Machine learning phases of matter | Nature Physics
Conservative Q-Learning for Offline Reinforcement Learning
Delendum - Research & Deep Tech Venture Fund
Open Paper
Prosumer - Wikipedia
Posthaven is the safe place for all your posts forever
Social deduction game - Wikipedia
Institute for Scientific Research
Co-Sci - Dashboard
Open Conference of AI Agents for Science: 2025
Machine learning | James Zou | Stanford
Owen Queen
Nitya Thakkar
Hi! | Federico Bianchi
OpenEvidence
How to spot a genius
CoCoSci
Long Reflection Reading List — EA Forum
OpenPoke: Recreating Poke's Architecture | Shlok Khemani
Getting free access to Poke's AI agent - by Jake Handy
OpenAI API base models are not sycophantic, at any size — LessWrong
Andy Zou
Center for AI Standards and Innovation (CAISI) | NIST
Unpopular Opinion: We'll Abandon Machine Learning as Main AI Paradigm | By Alberto Romero | TDS Archive
Want to predict/explain/control the output of GPT-4? Then learn about the world, not about transformers. — LessWrong
Explicitly unbiased large language models still form biased associations | PNAS