🐿️ ScourBrowse
LoginSign Up
You are offline. Trying to reconnect...
Copied to clipboard
Unable to share or copy to clipboard
🧮 Kolmogorov Bounds

Algorithmic Information, Compression Limits, Universal Prediction, Minimum Description

Classification errors distort findings in automated speech processing: examples and solutions from child-development research
arxiv.org·1d
🧠Machine Learning
Show HN: A short story on developing a long-context World-Model with no money
francesco215.github.io·14h·
Discuss: Hacker News
🧠Learned Codecs
The folk theorem of statistical computing: Fake-data simulation as posterior predictive checking
statmodeling.stat.columbia.edu·19h
⚔️Lean Theorem
Cracking the Density Code: Why MAF Flows Where KDE Stalls
towardsdatascience.com·16h
🔗Tailscale
Deep Dive: OpenAI's GPT-OSS
dev.to·5h·
Discuss: DEV
📊Quantization
WeakC4, or Distilling an Emergent Object
2swap.github.io·8h·
Discuss: Hacker News
🔲Cellular Automata
Compute Where It Counts: a trainable LLM sparsity enabling 4x CPU speed
crystalai.org·2d·
Discuss: Hacker News
🌊Streaming Algorithms
The "Super Weight:" How Even a Single Parameter can Determine a Large Language Model's Behavior
machinelearning.apple.com·2d·
Discuss: Hacker News
💻Local LLMs
Understanding Data Influence with Differential Approximation
arxiv.org·2d
🧠Machine Learning
Reproducing prospect theory with 'differentiable decision theories'
science.org·1d·
Discuss: Hacker News
🔲Cellular Automata
Quantifying Baseball Pitch Tunneling with K-Nearest Neighbors
runningonnumbers.com·3d·
Discuss: Hacker News
🌀Differential Geometry
Unplug and Play Language Models: Decomposing Experts in Language Models at Inference Time
arxiv.org·1d
🧠Intelligence Compression
The Price of Intelligence
cacm.acm.org·3d
💻Local LLMs
What Hugging Face reveals about the data economy of fine-tuning
research.portexai.com·17h·
Discuss: Hacker News
🌀Brotli Internals
On the Interplay between Graph Structure and Learning Algorithms in Graph Neural Networks
arxiv.org·2d
🧠Machine Learning
Inference Time Debiasing Concepts in Diffusion Models
arxiv.org·1d
🧠Machine Learning
LLMs are NOT Turing Complete (at train time), we need "train time recurrence"
fchaubard.github.io·6h·
Discuss: Hacker News
📼Tape Combinators
Busy Beaver Hunters Reach Numbers That Overwhelm Ordinary Math
quantamagazine.org·19h·
Discuss: Hacker News, Hacker News
🎞️Tape Combinatorics
Lessons from AI Safety for Businesses
svana.name·23h·
Discuss: Hacker News
🌍Cultural Algorithms
Non-linear Welfare-Aware Strategic Learning
arxiv.org·1d
🧠Machine Learning
Loading...Loading more...
AboutBlogChangelogRoadmap