Blog
Latest articles
7 min readLayoutLMv3: Understanding PDFs, Forms, and Documents With Layout Awareness
Microsoft's LayoutLMv3 pretrains on text, bounding boxes, and image patches together, enabling form understanding, receipt parsing, and document VQA without separate OCR fine-tuning.
4 min readNeptune.ai: Experiment Tracking for ML Teams That Outgrew Notebooks
Neptune.ai tracks ML experiments, stores artifacts and metrics, and enables team collaboration on model comparisons - bridging the gap between prototype notebooks and production model management.
9 min readLLM Cost Estimation: Budgeting for Multi-User AI Applications in Production
Step-by-step framework for calculating monthly active user workloads, tokens-per-session averages, and cloud margins before launching an AI feature.
11 min readRAG Evaluation: Implementing Ragas and TruLens for Production Pipelines
How to systematically measure retrieval context relevance, generation faithfulness, and answer correctness in production search systems.
14 min readHow Large Language Models Work: A Complete Guide Without the Math Overload
A plain-English guide to how LLMs actually work: tokens, attention, training vs inference, why they hallucinate, and what context windows mean for your workflow.
4 min readPEFT and LoRA: Fine-Tune a 7B LLM on a Single GPU in 2026
The PEFT library with LoRA and QLoRA enables fine-tuning 7B parameter LLMs on a single consumer GPU by updating only a small fraction of parameters, reducing VRAM from 14GB to under 5GB.
8 min readDeepSpeed: Train Models With Billions of Parameters on Limited GPUs
Microsoft's DeepSpeed enables training of 100B+ parameter models across distributed GPU clusters through ZeRO optimization stages, CPU offloading, and RLHF support.
4 min readZod v4: 100x Faster Validation and What Changed for TypeScript Developers
Zod v4 rewrites the parser engine for 100x faster validation on large schemas, adds z.file() and z.templateLiteral(), and cuts the core bundle by 57%.
10 min readEvaluation Metrics for Code-Generation LLMs: Beyond HumanEval Benchmarks
Standard benchmarks like HumanEval do not reflect real coding. Explore AST verification, compile checks, and unit test runners for agent evals.
9 min readAutomated Red-Teaming for LLMs: Simulating Attacks at Scale
Use secondary LLMs to systematically probe your production application for vulnerabilities, offensive outputs, and jailbreak weaknesses.
10 min readChain of Thought Prompting: 8 Patterns With Real Before-and-After Examples
Chain of thought prompting improves accuracy on multi-step reasoning by 10-40%. Eight specific CoT patterns with real before-and-after prompt examples.
8 min readThe Hidden Cost of Tool Switching: What We Measured With Our 4-Person Team
Gloria Mark's 23-minute refocus research applied to our real team. The formula for calculating what tool switching actually costs, with our own numbers.