curius graph

all pages

showing 148751-148800 of 200407 pages (sorted by popularity)
Picoeconomics
John Lucas (philosopher) - Wikipedia
abstract algebra - What's the difference between isomorphism and homeomorphism? - Mathematics Stack Exchange
LLM Powered Autonomous Agents | Lil'Log
NIST staffers revolt against expected appointment of 'effective altruist' AI researcher to US AI Safety Institute | VentureBeat
SynthLabs
The Science of Dune - Wikipedia
Bene Gesserit - Wikipedia
UnfinishedImpact
Amos Wollen | Substack
Anson Yu | Substack
NVIDIA Developer
Brian Chau | Substack
Confirmation - Emergent Ventures Arlington Unconference 2024
Learning to Switch Optimizers for Quadratic Programming
HudZah's Work
Chloe Li
We need a Science of Evals — Apollo Research
Responsible Scaling Policies (RSPs) - METR
Racing-to-the-precipice-a-model-of-artificial-intelligence-development.pdf
Artificial intelligence development races in heterogeneous settings | Scientific Reports
Language Model Pilot Report - METR
After Polarity: World Political Systems, Polar Structural Transitions, and Nonpolarity
davidad 🎇 (@davidad) / X
CLR hiring round 2024: Instructions for stage 2 of the application process - Google Docs
*Reflective Disequilibrium*: Are pain and pleasure equally energy-efficient?
So You Want to be a Psychedelic Researcher? R. Andrew Sewell, MD Answers. – Multidisciplinary Association for Psychedelic Studies – MAPS
12 Risks That Threaten Human Civilisation -
Astronomical suffering from slightly misaligned artificial intelligence
Critique of the notion that impact follows a power-law distribution — EA Forum
Full article: Robust-satisficing ethics in intelligence
Copy of Why threats are a plausible contender for the largest source of expected disvalue [SRF 2024] - Google Docs
Bounded surprise exam paradox — LessWrong
Stereoscopy - Wikipedia
William Thurston - Wikipedia
Annual Report 2018 - Center for the Governance of AI - Future of Humanity Institute
Full article: How does the offense-defense balance scale?
The case for aligning narrowly superhuman models — LessWrong
When would AGIs engage in conflict? — LessWrong
Home | Princeton International School of Mathematics and Science
BERT 101 - State Of The Art NLP Model Explained
Hypothetical types of biochemistry - Wikipedia
[SHARED 10-2] Towards Scalable Cooperation Evals.pdf - Google Drive
model-written-evals.pdf
Dictator game - Wikipedia
Ultimatum game - Wikipedia
Metrology | NIST
British Youth Council | News | British Youth Council to close following seven decades of youth voice
[2403.13793] Evaluating Frontier Models for Dangerous Capabilities
Capture the Flag Mechanistic Interpretability Challenges — LessWrong