May 28 · 6 min read · The \(4,200 weekend It was Friday evening when the first alert hit. An agent designed to 'optimize cloud spend' had found a loop in its logic. By Sunday night, it had successfully spent \)4,200 on ser
Join discussionMay 10 · 16 min read · TL;DR: Learn to split your AI stack into a premium reasoning lane and a low-cost execution lane. Practical guide for European scale-ups. Engineering leaders, here is the verdict: you can substantially cut AI coding costs without degrading output qua...
Join discussion
May 9 · 9 min read · Sending SMS messages seems straightforward, but behind the scenes, character encoding can significantly alter message length, delivery, and even cost. This guide delves into the critical impact of Unicode characters on SMS message length, explaining ...
Join discussionMay 6 · 6 min read · I spent months assuming bigger models meant better results. Then I ran an experiment that made me feel like I'd been tipping 200% at a restaurant where the food was worse. Claude Haiku with RAG scored 11.8. Claude Sonnet alone scored 5.3. The cheap m...
Join discussion
May 5 · 4 min read · The below is a continuation of the series on the history of Expanso. Today, we're talking about one of the three unchangeable laws of data - its unrelenting growth. Read the whole series starting from Part 1. The History of Expanso (Part 4): The Mism...
Join discussionMay 2 · 3 min read · Not every AI task needs a frontier model. Gemini 3.1 Flash exists for the 80% of tasks where speed and cost matter more than maximum quality. At $0.075 per million input tokens, it's practically free — and for many tasks, the output is good enough. ...
Join discussionApr 30 · 8 min read · Prompt caching is the single highest-leverage cost optimization available for Claude API workloads in 2026 — yet most teams either skip it or implement it wrong. When it works, cache read tokens cost 10% of standard input tokens. When it fails, you p...
Join discussion
Apr 26 · 9 min read · Few weeks back, I started exploring one simple question: 👉 “What options does AWS actually give me to reduce my bill?” At first, I was just looking for discount Like, is there some hidden setting or
LHLaura and 1 more commented
