News
AI, cybersecurity, machine learning, scraping & programming news.
How do Necco wafers, paper receipts, and farmers almanacs still exist?
A German startup has completed the first commercial rocket launch to reach orbit from continental Europe, carrying five small satellites. Isar Aerospace's success marks a shift in the European space industry, which has historicall...
General Quantification of Covariate and Concept Shifts
Distribution Shift Is a Broken Promise Every deployed model makes an implicit bet: that the data it sees at inference will look like the data it trained on. When that bet fails, performance degrades silently and sometimes catastro...
Data Scarcity and Model Sparsity: Mixtures-of-Experts Overfit More to Repeated Data
When Running Out of Data Breaks Sparse Models The internet's text is finite. As language model training scales toward and beyond the limits of human-written corpora, repeating data has become standard practice. Muennighoff et al....
Distance generalization in transformers: why bother with positional encoding?
Positional Encoding May Be Hurting Your Transformer Transformers are everywhere, and positional encoding is considered foundational. Every major production model, from Llama to DeepSeek, uses RoPE (Rotary Position Embeddings) to t...
TART: A Modular Tool for Technique-Aware Audio-to-Tablature Guitar Transcription
Automatic Music Transcription for guitar has long been stuck on the wrong side of the difficulty curve compared to piano. Piano AMT hit high note-level accuracy years ago through CRNN models and large paired datasets, but guitar t...
MindTopo: Can Foundation Models Reason in Topological Space?
Piaget argued that children develop spatial understanding in a fixed sequence: topological relations come first, followed by projective and Euclidean ones. The child first grasps that two points are connected, that one region encl...
Caption-once, Frames-on-Demand: Visual-Need Routing for Budget-Aware Agentic Long Video Understanding
Long video understanding on edge devices runs into a fundamental tradeoff. You can subsample visual tokens and hope the model still catches what matters, or you can convert the video into text captions and lose the fine-grained vi...
From Specs to Apps: Verifying and Monitoring Models of Signal and WhatsApp
The Signal protocol secures daily messages for billions of people across WhatsApp, Signal Desktop, Facebook Messenger, and Google Messages. Years of formal analysis in the computational and Dolev-Yao settings have produced strong...
The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement
Modern AI systems can write code, reason through graduate-level science, and plan multi-step research workflows. But every improvement they undergo still requires humans to decide what to fix, build the resources to fix it, and ju...
BlueSTAR: Tiered Agentic Architecture for Autonomous Cyber Defense
Security analysts are losing the speed war. Average breakout time, from initial access to lateral movement onto a second host, is now 29 minutes, and the fastest observed is 27 seconds. Meanwhile, defenders still rely on human jud...