curius graph

all pages

showing 35401-35450 of 200407 pages (sorted by popularity)
[2605.10310] Positive Alignment: Artificial Intelligence for Human Flourishing
Eval Cooperativeness May Be a Scalable Mitigation for Eval Gaming — LessWrong
A List of Research Directions in Character Training — LessWrong
Research Reflections — LessWrong
Abram Demski at MATS: Summer 2026
Building and evaluating model diffing agents — AI Alignment Forum
[2510.17941] Believe It or Not: How Deeply do LLMs Believe Implanted Facts?
Side Effects of Character Training: Quantifying Cross-Constitution Drift in LLMs
Mind the Future | Richard Ngo | Substack
[2607.26069] AI Security Priorities: A Field-Wide Agenda
Dissertation
MAIS/papers/P1/MAIS-P1.pdf at main · lionellevine/MAIS
What is prosaic alignment?
Ryan Greenblatt on X: "I was the main person doing transcript analysis for this investigation of the Hugging Face incident. My main takeaway: We don't have good approaches for understanding/overseeing the activity and aims of AI 'swarms'. I semi-jokingly called our efforts a "slop-vestigation" because" / X
Geoffrey Irving on X: "A big question in AI safety is how much and what kinds of evidence will convince people there is danger. But alongside posts about the excellent METR + Redwood HuggingFace attack report, it is worth taking a walk through 73 years of reward hacking history. 🧵 https://t.co/ABHcoND9fn" / X
inspiration is the how the universe delivers the answers to our prayers
Comfort Zone Exploration — LessWrong
Partner as a state of being - by Kylie 曾 Tseng
Design With FontForge: Trusting Your Eyes
Design With FontForge: Creating ‘o’ and ‘n’
Surrender as a non-stupid life strategy - by Sasha Chapin
Mango Sago Cheesecake Recipe | Alchenny
PRISM - Political Refraction and Identity Spectrum Model
PyTorch in One Hour | Sebastian Raschka, PhD
Why GEMM is at the heart of deep learning « Pete Warden's blog
The Grateful Bastards - by Vishal Dayama
MCAT Review Sheets.pdf - Google Drive
prompts/prompts/multi_target_binder_design_prompt.md · Anthropic/claude-protein-binder-design at main - https://huggingface.co/
New talk! “How To Explain Things Real Good”
The Logical Fallacy of Generalization from Fictional Evidence — LessWrong
Infinite Certainty — LessWrong
Overly Convenient Excuses — LessWrong
The Quotation is not the Referent — LessWrong
Lost Purposes — LessWrong
Humans Are Just Stochastic Parrots | Ryan Dahl
ode to the mets | arielle lok
My Childhood Death Spiral — LessWrong
The Affect Heuristic — LessWrong
Raised in Technophilia — LessWrong
The Meaning of Right — LessWrong
My Bayesian Enlightenment — LessWrong
The Second Law of Thermodynamics, and Engines of Cognition — LessWrong
Just Lose Hope Already — LessWrong
Science: Do It Yourself — LessWrong
How to Do Philosophy
Helpless Individuals — LessWrong
You Weren't Meant to Have a Boss
Savanna Poets — LessWrong
Select
Litherum: Implementing a GPU's Programming Model on a CPU