curius graph

all pages

showing 80301-80350 of 203087 pages (sorted by popularity)
The Adventure of the Errant Hardware
Reading ancient scrolls – Casey Handmer's blog
[2310.02984] Scaling Laws for Associative Memories
Local vs. Distributed Coding - Persée
Investigating the learning coefficient of modular addition: hackathon project — AI Alignment Forum
Large language models in the labyrinth: Possibility spaces and moral constraints - Victor Møller Poulsen, Simon DeDeo, 2023
JOSCID.pdf
Intrinsic Drives and Extrinsic Misuse: Two Intertwined Risks of AI
What's with ML software and pickles? - Made of Bugs
Maithra Raghu | On AGI and Self-Improvement
GPT-2030 and Catastrophic Drives: Four Vignettes
Policy Brief | The AI Regulatory Alignment Problem | Stanford HAI
Large Language Models Capture-the-Flag (LLM CTF) Competition
Who Controls OpenAI? - Bloomberg
PsyArXiv Preprints | Folk Psychological Attributions of Consciousness to Large Language Models
Ensemble of Exemplar-SVMs for Object Detection and Beyond
randomfun/knn_vs_svm.ipynb at master · karpathy/randomfun
The Myth of RAM, part I
Incidental polysemanticity MOC | Victor Lecomte
The Power of Bidiagonal Matrices – Nick Higham
AI Safety in a World of Vulnerable Machine Learning Systems | FAR AI
Compromising LLMs: The Advent of AI Malware
Better, Cheaper, Faster LLM Alignment with KTO - Contextual AI
Refusal mechanisms: initial experiments with Llama-2-7b-chat — LessWrong
Paving the way to efficient architectures: StripedHyena-7B, open source models offering a glimpse into a world beyond Transformers
Diff-in-Means Concept Editing is Worst-Case Optimal | EleutherAI Blog
ML Safety Newsletter #11
microsoft/phi-2 · Hugging Face
Look Before You Leap: A Universal Emergent Decomposition of Retrieval Tasks in Language Models
Einops, retrospective of 5 years
CSC2541 Winter 2022
Gentleness and the artificial Other - Joe Carlsmith
Survey of 2,778 AI authors: six parts in pictures
LLM Training and Inference with Intel Gaudi 2 AI Accelerators | Databricks Blog
Routers Roasting on an Open Firewall: the KV-botnet Investigation - Lumen
Data Pruning at Scale - by Haoli Yin - Haoli’s AI Insights
Sparse Autoencoders Work on Attention Layer Outputs — AI Alignment Forum
swp0000.dvi
Cumulants, and Cumulant Generating Functions
cuda_mode_lecture2 - Google Slides
A Reply to Makelov et al. (2023)’s “Interpretability Illusion” Arguments
start leveraging einx get_at for extra clarity · lucidrains/vector-quantize-pytorch@3af4110
Grand-master Level Chess without Search
Social science research topics for global health and wellbeing | Open Philanthropy
Notes on control evaluations for safety cases — AI Alignment Forum
Portable Evaluation Tasks via the METR Task Standard - METR
Some costs of superposition — AI Alignment Forum
task-standard/examples at main · METR/task-standard
Fine-Grained Human Feedback | Databricks Blog
Further notes on Birkhoff-von Neumann decomposition of doubly stochastic matrices