curius graph

all pages

showing 151751-151800 of 200407 pages (sorted by popularity)
Echoborg - Wikipedia
Cyranoid - Wikipedia
Can You Share Your Network Configurations?
‪Erik Jenner‬ - ‪Google Scholar‬
How to prevent collusion when using untrusted models to monitor each other
Schelling game evaluations for AI control — LessWrong
[2501.00070] ICLR: In-Context Learning of Representations
[2307.10163] Rethinking Backdoor Attacks
Fable of the Dragon-Tyrant - YouTube
fastestuniverse.pdf
‪MATS Research‬ - ‪Google Scholar‬
My Work with Chris Lakin - guy
Shtetl-Optimized » Blog Archive » Five Worlds of AI (a joint post with Boaz Barak)
Which Computational Universe Do We Live In? | Quanta Magazine
ri5svetu.pdf
AlphaEvolve.pdf
Collisteru | collisteru.net
When bits of optimization imply bits of modeling: the Touchette-Lloyd theorem — LessWrong
A Message from 10 Downing Street - SoTA Letters
Radimentary | "Everything can be made radically elementary." ~Steven Rudich
Looking Out from the Isolator: David's Perception of the World
Lecture 48 - Adjoint Functors
Inside View Merch Shop | Redbubble
About | Sarah Constantin
Daphnia Labs - Longevity List
[2401.06102] Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models
[2510.01070] Eliciting Secret Knowledge from Language Models
Training Language Models to Explain Their Own Computations
[2508.14802] Privileged Self-Access Matters for Introspection in AI
[2512.13933] Decomposing Non-Markovian History Dependence
[2512.13936] Tractable Model for Tunable Non-Markovian Dynamics
[2009.05041] Understanding the Role of Individual Units in a Deep Neural Network
[2202.05262] Locating and Editing Factual Associations in GPT
4f5c422f4d49a5a807eda27434231040-Paper.pdf
pdf
[2407.04694] Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs
[2506.05068] Does It Make Sense to Speak of Introspection in Large Language Models?
2412.08686
[2412.08686] LatentQA: Teaching LLMs to Decode Activations Into Natural Language
[height=18pt]figures/misc/stethoscope.png Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models
Towards eliciting latent knowledge from LLMs with mechanistic interpretability
Eliciting Secret Knowledge from Language Models
Particle zoo - Wikipedia
My Dating Heuristic — LessWrong
Opinion | Disney World Is the Happiest Place on Earth, if You Can Afford It - The New York Times
Constructive developmental framework
Summary of Kegan Stage 5 Principles
Mimetic Desire - Adaptive Good
Kimi Linear: An Expressive, Efficient Attention Architecture
Why Your Next Hackathon Should Be "Useless" - The Philosophy Behind CamHack - James Leung's Notes