Smarter Pixels: Turbocharging Visual AI with Semantic Compression by Arvind Sundararajan
dev.to·5h·
Discuss: DEV
🧠Neural Compression
Learning languages with the help of algorithms
johndcook.com·1d·
Discuss: Hacker News
🧮Kolmogorov Complexity
2025-09-17: Classic Machine Learning Models and XAI Methods
ws-dl.blogspot.com·1d·
Discuss: ws-dl.blogspot.com
🧠Machine Learning
Language Models Wrestle with Gaps in Understanding
cacm.acm.org·6h
💻Local LLMs
Network representations reveal structured uncertainty in music
arxiv.org·19h
🎼Computational Musicology
Coding as the epicenter of AI progress and the path to general agents
interconnects.ai·8h·
Discuss: Hacker News
📏Code Metrics
Such a Classic
blog.hermesloom.org·1d·
Discuss: Hacker News
🧪Binary Fuzzing
Building tenets: Intelligent context aggregation for AI pair programming
jddunn.github.io·6h·
Discuss: Hacker News
🌀Brotli Internals
A Tandem of GPT-5 And [Mystery Model] Has Beaten the Best Human Coders
thealgorithmicbridge.com·7h
🔲Cellular Automata
How to build AI scaling laws for efficient LLM training and budget maximization
news.mit.edu·2d
🧮Kolmogorov Bounds
Building Coding Agents via Entropy-Enhanced Multi-Turn Preference Optimization
arxiv.org·1d
🧠Learned Codecs
The Case for Compact AI – Communications of the ACM
dl.acm.org·2d·
Discuss: Hacker News
🌊Streaming Algorithms
The huge AI security hole
aardvark.co.nz·6h
🔓Hacking
AI Solves the Algorithmic Conundrum: Adaptive Heuristics for Any Problem by Arvind Sundararajan
dev.to·1d·
Discuss: DEV
⚡Incremental Computation
Benchmark code for evaluating different ASR packages and APIs
github.com·13h·
Discuss: Hacker News
🎙️Whisper
Post-Hoc Split-Point Self-Consistency Verification for Efficient, Unified Quantification of Aleatoric and Epistemic Uncertainty in Deep Learning
arxiv.org·1d
📊Quantization
AssoCiAm: A Benchmark for Evaluating Association Thinking while Circumventing Ambiguity
arxiv.org·19h
🌳Context free grammars
Cognitive Blueprints: Mapping Thought for Smarter AI by Arvind Sundararajan
dev.to·7h·
Discuss: DEV
🔲Cellular Automata
[ARC-AGI-2 SoTA] Efficient Evolutionary Program Synthesis
ctpang.substack.com·1d·
Discuss: Substack
⚡Incremental Computation
The Unseen Variable: Why Your LLM Gives Different Answers (and How We Can Fix It)
hackernoon.com·2d
💻Local LLMs