/ Writing

Notes from the field

Articles on AI, LLM inference, backend systems and cloud — most of them published on Medium. Subscribe via RSS.

Featured AI OpenDynamicGGUF: An Open, Measured, Reproducible Optimizer for Per-Tensor GGUF Quantization Why uniform Q4_K_M is leaving quality on the table — and how an open 15-step pipeline picks the right bits for every tensor, under your hardware budget. Medium · September 12, 2026 · 35 min read

2026

Sep 12, 2026 OpenDynamicGGUF: An Open, Measured, Reproducible Optimizer for Per-Tensor GGUF Quantization Why uniform Q4_K_M is leaving quality on the table — and how an open 15-step pipeline picks the right bits for every tensor, under your hardware budget. AI Medium · 35 min read
Sep 05, 2026 Stop Writing Nested Try/Except Hell: The AWS Service That Replaces Your Entire Workflow Engine If your Lambda functions call other Lambda functions wrapped in retry logic wrapped in more retry logic, you're solving a problem AWS already solved for you. Cloud Medium · 6 min read
Sep 04, 2026 The Data Paradox No One Talks About: Why AI Companies Are Secretly Building Fake Enterprises to Train Real Models You need sensitive data to train a system that detects sensitive data — but you're legally forbidden from using it. Here's the workaround nobody's talking about. AI Medium · 10 min read
Aug 30, 2026 Airbnb Changed Login Completely — The Server Now Decides How You Authenticate How Airbnb's engineering team scrapped hardcoded login logic, moved the brain to the server, and cut client code by 60% in the process. Engineering Medium · 4 min read
Aug 25, 2026 Spot Instances: The Secret to Cutting Cloud Costs by Up to 90% (And Why Every Modern Team Should Care) Cloud computing changed how we build and scale applications — and introduced runaway costs. How Spot capacity cuts the bill by up to 90%, and how to use it safely. Cloud Medium · 5 min read
Aug 23, 2026 I Tried Meta’s “Segment Anything Model”— And Now I Can’t Look at Photos the Same Way The AI tool that turns any image into perfectly cut-out objects with one click — and why designers, doctors and self-driving engineers are obsessed with it. AI Medium · 3 min read
Aug 06, 2026 Why Your Database Wasn’t Built for AI Agents (And How to Fix It) A practical guide to redesigning database architecture for the agentic era. AI Medium · 9 min read
Jul 26, 2026 OpenDynamicGGUF: An Open-Source Answer to Unsloth’s “Dynamic” GGUF Quantization How a new alpha-stage project makes mixed-precision LLM quantization transparent, reproducible and measurable. AI Medium · 9 min read
Jul 15, 2026 LLM Quantization The optimisation that put Llama 3, Qwen, DeepSeek and Mistral on consumer GPUs and laptops — what quantization is, and what names like Q4_K_M actually mean. AI Medium · 8 min read