Browsing Tag
nlp
32 posts
Embeddings Cannot Say No: An Intent Detector’s Real Numbers
My message detector worked on my test set. On messages it had never seen, it missed one real…
Building an Open Turkish EV Charging Intent Dataset
Electric-vehicle assistants rarely have just one job. A short Turkish question may ask for a nearby station, a…
RAG – Memory Systems
We need memory to store the previous conversational history. For example: Previous question is: User: File handling in…
How Transformer Architecture Works — Encoder, Decoder, Tokens, and Context
Transformers changed NLP because they stopped treating text as a simple left-to-right chain. Instead of reading one token…
I built the first open benchmark for federal contracting AI. Here’s what it shows about frontier LLMs.
If you ask GPT-4o or Claude to extract Federal Acquisition Regulation clause numbers from a federal solicitation, a…
Did My LoRA Learn Tenacious Style—or Just Memorize Augmented Patterns?
In Week 11 Tenacious-Bench, we trained a LoRA adapter on Tenacious-style B2B sales emails using Supervised Fine-Tuning (SFT).…
Understanding Text Similarity with Embeddings and Cosine Similarity
How to measure semantic similarity between sentences using modern NLP techniques Introduction Have you ever wondered how search…
Parametric Hubris: Empirical Evidence That Tool Availability Does Not Equal Tool Usage in Frontier Language Models
Parametric Hubris: Empirical Evidence That Tool Availability Does Not Equal Tool Usage in Frontier Language Models Frontier large…
How to Detect Energy Sentiment Anomalies with the Pulsebit API (Python)
How to Detect Energy Sentiment Anomalies with the Pulsebit API (Python) We recently observed a striking anomaly in…
Optimal Turkish Subword Strategies II: What WordPiece Learns from Turkish Morphology
Turkish is generous with morphology. A single lemma can grow into a long surface form — case, possession,…
