curius graph

all pages

showing 13951-14000 of 160880 pages (sorted by popularity)
Self-exfiltration is a key dangerous capability
The prototypical catastrophic AI action is getting root access to its datacenter — LessWrong
Paul Christiano
VDT: a solution to decision theory — LessWrong
Rediscovering British Progress
Towards a scale-free theory of intelligent agency — AI Alignment Forum
A Mechanistic Interpretability Analysis of Grokking - AI Alignment Forum
ActivityWatch - Open-source time tracker
Deep Forgetting & Unlearning for Safely-Scoped LLMs — AI Alignment Forum
We Live In a Golden Age of Interoperability
Vitalik Buterin - Wikipedia
About — EleutherAI
John Muir - Wikipedia
how to be happy in san francisco - by Ava
Social behavior curves, equilibria, and radicalism – Unexpected Values
Applause Lights — LessWrong
The Talent Agent Model | Entrepreneurs First
QuantilizersSaferAlternative.pdf
How did Warren Buffett get rich? This boy lived to answer the question - Deseret News
Many-worlds interpretation
What is Evidence? — LessWrong
We may finally crack Maths. But should we?
Zvi’s Thoughts on the Survival and Flourishing Fund (SFF) - LessWrong
Latent Space (Paper Club & Other Events) · Luma
aman.ai • the art of artificial intelligence
13 Signs You Used ChatGPT To Write That
When Aaron Swartz met Paul Graham his life–and the entire internet–changed forever
visualizing who you want to be
1Day Sooner
Georgism
I am neil
Church–Turing thesis
How I taught an AI to think like a painter
Having Kids
Hutter Prize
In Defense of Punch Bug. Or, Against Social Ownership of the… | by Duncan A Sabien | Medium
Jeff Kaufman
British and American Connotations
Tom Preston-Werner - Wikipedia
AGI is Still 30 Years Away — Ege Erdil & Tamay Besiroglu
Haskell Programming.pdf
Softmax function
Shallow review of technical AI safety, 2024 — LessWrong
The Citizen Lab - University of Toronto
Problem of universals - Wikipedia
Dutch book theorems
Papa's Lessons Are More Crucial than Ever in the Age of AI
LessOnline 2025
On how various plans miss the hard bits of the alignment challenge — LessWrong
Affective Death Spirals — LessWrong