curius graph

all pages

showing 14151-14200 of 160880 pages (sorted by popularity)
Carbon chauvinism
Are You Living in a Simulation?
The Institute
Express interest in an "FHI of the West" — LessWrong
Depth-first search - Wikipedia
LLMs can learn about themselves by introspection — LessWrong
socketteer/loom: Multiversal tree writing interface for human-AI collaboration
[2101.00190] Prefix-Tuning: Optimizing Continuous Prompts for Generation
Active learning (machine learning)
Optimal experimental design - Wikipedia
Introduction | Causal Incentives Working Group
Obsidian Web Clipper
AI Safety Seems Hard to Measure
Making deals with early schemers — LessWrong
The Screwtape Letters - Wikipedia
Benefits of Assistance over Reward Learning | OpenReview
[1606.03137] Cooperative Inverse Reinforcement Learning
Towards Alignment Auditing as a Numbers-Go-Up Science — LessWrong
Mathematics in Lean — Mathematics in Lean 0.1 documentation
About
Why Greatness Cannot Be Planned: The Myth of the Objective | SpringerLink
Home — Gordon Brander
An open system to manage data without a central server | IPFS
Overcoming Bias: Anthology
[2510.13786] The Art of Scaling Reinforcement Learning Compute for LLMs
book.bionumbers.org
Anthropic Bias – Complete Text | The Anthropic Principle
Doomsday argument - Wikipedia
There are exponentially many vectors with small inner product | Longest path search
posthuman.pdf
Shard Theory: An Overview — LessWrong
Why Pay Attention To The Output Of Statistical Machines?
Hierarchical Reasoning Model
The 'Neglected Approaches' Approach: AE Studio's Alignment Agenda — LessWrong
Jakob N. Foerster
Looking Back at the Future of Humanity Institute—Asterisk
Building up to an Internal Family Systems model — LessWrong
Nick Land-Meltdown
Geometric Rationality is Not VNM Rational — LessWrong
Incentive compatibility
In the Cells of the Eggplant
Rationality and refrigerators | Meta-rationality
Big O
samwho
Orbit
Christopher Sims
Metastability - Wikipedia
[2404.13076] LLM Evaluators Recognize and Favor Their Own Generations
Startups to Follow
How To Grow (Almost) Anything — MIT Media Lab