curius graph

all pages

showing 151051-151100 of 200407 pages (sorted by popularity)
Cosine similarity - Wikipedia
A Turing test of whether AI chatbots are behaviorally similar to humans | PNAS
yutxie/ChatGPT-Behavioral
Large language models show amplified cognitive biases in moral decision-making | PNAS
Having multiple selves helps learning agents explore and adapt in complex changing worlds | PNAS
pdf
Joscha Bach on X: "The universality hypothesis of AI/machine learning is the more important and less known sibling of the scaling hypothesis." / X
Is a doomsday catastrophe likely? | Nature
[2503.08688] Randomness, Not Representation: The Unreliability of Evaluating Cultural Alignment in LLMs
[2503.17181] A Study of LLMs' Preferences for Libraries and Programming Languages
Causal graph - Wikipedia
[2509.09396] LLMs Don't Know Their Own Decision Boundaries: The Unreliability of Self-Generated Counterfactual Explanations
[astro-ph/0512204] How unlikely is a doomsday catastrophe?
How To Live In A Simulation*
Propositions Concerning Digital Minds and Society
[cs/0004001] A Theory of Universal Artificial Intelligence based on Algorithmic Complexity
‪Sean O'Brien‬ - ‪Google Scholar‬
Forum | OpenReview
myracheng/elephant
[2502.08177] SycEval: Evaluating LLM Sycophancy
Parlor House ✦ Welcome to the Parlor!
🏛️ The next evolution of The Commons - The Commons
Esben Kran
Seldon Lab
johnnylin.co
Binary Cross Entropy/Log Loss for Binary Classification - GeeksforGeeks
jbloomaus.com/about/
Home | Catalyze
[2412.01784] Noise Injection Reveals Hidden Capabilities of Sandbagging Language Models
panickssery projects
Caithrin Rintoul
Quentin Anthony on X: "I was one of the 16 devs in this study. I wanted to speak on my opinions about the causes and mitigation strategies for dev slowdown. I'll say as a "why listen to you?" hook that I experienced a -38% AI-speedup on my assigned issues. I think transparency helps the community. https://t.co/Qc7nSFj6kR" / X
Codex IDE extension
[2509.26537] The Loss Kernel: A Geometric Probe for Deep Learning Interpretability
Science through Computation
A New National Purpose: Accelerating UK Science in the Age of AI
ScienceIO
Research Software Engineers | Research Software Engineers International
Home - Society of Research Software Engineering
AlgorithmsIlluminated2Roughgarden.pdf
Innovator Circles
List comprehension - Wikipedia
Joseph Bloom - Independent AI Safety Research | Manifund
Home - CHIA
Trustworthy and untrustworthy models — AI Alignment Forum
‪Owain Evans‬ - ‪Google Scholar‬
Peter N. Salib
felixbinder/introspection_self_prediction: Code for experiments on self-prediction as a way to measure introspection in LLMs
[1711.09883] AI Safety Gridworlds
Preventing Side-effects in Gridworlds