chatstyle: a C++ core and a Python app for comparing writing styles in chats (Russian only, so far)
Disclosure. Most of the code, the tests and the first draft of this article were produced with an AI...
Oct 5, 20265 min read0 reactions0 comments
Back to articles Oct 5, 2026 
Oct 4, 2026
Oct 2, 2026
Oct 1, 2026
Tag archive
#nlp
H
Oct 5, 2026How well do AI models read Tanglish? I tested 13 of them
This is a submission for the Kaggle Benchmarking Challenge What I Benchmarked I'm a Tamil...
Oct 5, 20265 min read0 reactions0 comments
T
Oct 5, 2026The 16x Context Trick: How Latent Context Models Finally Made Compression Work
One-paste order for Medium's new-story editor: title → body → diagrams → notebook link →...
Oct 5, 20264 min read0 reactions0 comments
W
Oct 4, 2026Why WER lies to you in production IVR
Part 1 of the CAFA-IVR series. Your ASR dashboard is green and your callers are furious. Word error...
Oct 4, 20265 min read0 reactions0 comments
AI Search Visibility Metrics: 10 KPIs to Track for ChatGPT, Gemini and Perplexity
TL;DR: AI search visibility metrics help you measure how often your brand appears in answers from...
Oct 4, 202610 min read1 reactions0 comments
O
Oct 4, 2026One-Hot Encoding, Bag of Words > (BoW), TF-IDF, Unigram, Bigram, Trigram and N-Gram
This note follows the concepts and terminology presented in the supplied lecture material and adds...
Oct 4, 202610 min read0 reactions0 comments
Can AI Really Detect Fake News? What the Research Shows
Why I Looked Into This I work with data every day, and I wanted to know one thing. Can AI...
Oct 2, 20264 min read0 reactions0 comments
H
Oct 2, 2026How to extract clean article text, author and date from news URLs
Turn a list of news and blog URLs into clean text or Markdown with title, author, publish date, site, tags and word count.
Oct 2, 20263 min read0 reactions0 comments
A
Oct 2, 2026AstaBrief 8B: How AllenAI Trained a Small Open Model to Generate Cited Scientific Reports
AstaBrief 8B: How AllenAI Trained a Small Open Model to Generate Cited Scientific...
Oct 2, 20265 min read0 reactions0 comments
A
Oct 2, 2026A word's frequency rank is not its difficulty: grading words for a placement test
We run Lingvoberry, a reader where you tap a word in a graded book to save it. To place a new user on...
Oct 2, 20263 min read0 reactions0 comments
I Trained an Open Decision Model on a Free GPU in 46 Minutes. On My Tests, It Beat Laya.
Typic, an open 400M decision model: one forward pass, a probability per option, trained on a free Kaggle T4 in 46 minutes.
Oct 1, 20266 min read0 reactions0 comments
S
Oct 1, 2026Shopping search translation is mostly query expansion: what 941 real queries showed
60% of Hebrew shopping queries get LONGER on the way to the marketplace's English: audience and bundle words, not translation.
Oct 1, 20263 min read0 reactions0 comments