Tech Tips, Tricks & Trivia

GitHub Copilot is moving to usage‑based billing on June 1, 2026, where token consumption (input, output, cached) directly affects costs. To optimize tokens, you need to reduce unnecessary context, use caching, and structure prompts efficiently. 1 2 3 4 5 How Copilot Uses Tokens Input tokens → what you send (code, prompts, context). Output tokens → what Copilot generates. Cached tokens → reused context (cheaper than new input). Context loading (files, repo, history) often consumes 80–90% of tokens, not the generated code itself. 5 Practical Strategies to Optimize Token Usage 1. Control Context Aggressively Avoid opening large/unrelated files while prompting. Limit selection scope before asking Copilot. Exclude build, log, and generated files at the enterprise level (e.g., /target/**, *.class, *.xml). 4 2. Break Tasks into Micro‑Operations ❌ Bad: “Refactor entire microservice.” ✅ Better: “Refactor this method to use reactive pattern.” Smaller scope = fewer files scanned = fewer tok...

This Week I Learned -  * AI is influencing not only how fast code is written, but which languages and tools developers use. -  Octoverse 2025   *  GitHub Copilot CLI for Beginners -  * Apple's Support app update v5.13 accidentally included CLAUDE.md files , which are configuration documents used to guide Anthropic's Claude Code AI coding assistant on codebase architecture and rules. Apple quickly released v5.13.1 to remove the files, exposing a rare view into their use of third-party AI tools for app development while highlighting a build process oversight at the highly secretive company. * Claude sometimes refuses or postpones work based on inferred time/context, possibly to manage token limits, avoid rushed outputs, or simulate thoughtful behavior. * As A.I. makes the production of knowledge work more and more efficient, the job of presenting, debating, lobbying, arm-twisting, reassuring or just plain selling the work appears to be rising in importance. ...

Open Food Facts is the largest and more comprehensive open database on the planet, by far. The Open Food Facts Slack  (open to all) has several channels for discussions, updates, and collaborations. I’ll keep sharing interesting facts I come across in the conversations there, right here: *  Pierre (teolemon) - The data (is)...legally acquired, through crowdsourcing and/or AI extraction from Crowdsourcing or existing OFF data. We don’t allow scraping for legal reasons. *  Alex Bourreau - I made a small tool to check what your contributions to Open Food Facts are used for : https://contributionreuses.bourreau.dev/ Enter your OFF username and it shows you a list of scientific articles that relied on data of products you've created ! *  James Addison  -  OpenFoodFacts does have methods to detect products where errors seem likely; it tracks those errors and distributes them to registered volunteers, who then help by reviewing the errors, often fixing them wher...