curius graph

all pages

showing 151351-151400 of 200407 pages (sorted by popularity)
Active inference and epistemic value
The Geometric Expectation — LessWrong
LogicalInduction.pdf
Visualizing Bayes Theorem
Clouds and eggplants | Meta-rationality
Steering Vector Playground
Consider donating to AI safety champion Scott Wiener – Unexpected Values
Hashing
[2509.25369] Generative Value Conflicts Reveal LLM Priorities
kellycyy/AIRiskDilemmas · Datasets at Hugging Face
[2505.14633] Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas
[PDF] Will AI Tell Lies to Save Sick Children? Litmus-Testing AI Values Prioritization with AIRiskDilemmas | Semantic Scholar
[2501.15463] Mind the Value-Action Gap: Do LLMs Act in Alignment with Their Values?
kellycyy/LitmusValues
Binary search tree - Wikipedia
[2407.18163] Statistical optimal transport
[2510.07686] Stress-Testing Model Specs Reveals Character Differences among Language Models
[2504.15236] Values in the Wild: Discovering and Analyzing Values in Real-World Language Model Interactions
[1610.01644] Understanding intermediate layers using linear classifier probes
jifanz/stress_testing_model_spec · Datasets at Hugging Face
2504.15236
Language Models Are Capable of Metacognitive Monitoring and Control of Their Internal Activations
AssistanceZero: Scalably Solving Assistance Games
2012.08347
1610.01644
[1901.08644] Ablation Studies in Artificial Neural Networks
[2310.11667] SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents
[2405.10632v3] Beyond static AI evaluations: advancing human interaction evaluations for LLM harms and risks
[2212.09746] Evaluating Human-Language Model Interaction
DigiKey - YouTube
Introduction to FPGA - YouTube
If you're 18 you should be sidequestmaxxing - Elliot Lindberg
synestheticworks.com/links/
[2410.13787] Looking Inward: Language Models Can Learn About Themselves by Introspection
[2407.10188] Unexpected Benefits of Self-Modeling in Neural Systems
Peter Hase
Finding the Words to Say: Hidden State Visualizations for Language Models – Jay Alammar – Visualizing machine learning one concept at a time.
2407.10188
[2305.17375] Attention Schema in Neural Agents
Self-prediction acts as an emergent regularizer — LessWrong
[1902.00506] The Hanabi Challenge: A New Frontier for AI Research
Theory of Diversity (RL) - ueaj - Obsidian Publish
Effects of Awareness on the Control of Attention - PubMed
cmnd2RLCT.pdf
2308.12108
Towards Hodge-podge Alignment — LessWrong
[1711.05101] Decoupled Weight Decay Regularization
About | Adam Scherlis
Adam Scherlis
The Neural Network Zoo - The Asimov Institute