We’ve been running a series of experiments using ChatGPT 5.4 integrated into a website chatbot across different environments: 🌐 a main website 🎯 Goal: simulate realistic user behavior and observe how the model responds over time. ⚙️ Test setup The chatbot is designed to (no self promo here, just context): 📌 answer strictly based on website content (RAG-like approach) Over time, we intentionally
Last Tuesday I lost about three hours to a regression in our checkout service. The cart total was off by a cent on certain promo combinations, and the only signal was a Slack ping from finance with a screenshot. No stack trace. No exception. Just wrong numbers. I did what I always do first. I opened the diff for the last deploy, scrolled, squinted, and tried to feel my way to the bug. Forty minute
I Built a VS Code Extension to Bring IntelliJ’s “Show History for Selection” Experience If you come from IntelliJ, you probably miss one super useful feature in VS Code: Show history for selected lines. I built a new extension to solve exactly that. Show History for Selected Code This extension helps you inspect Git history for a specific code selection, not just the whole file. Shows commit h
How I added LLM fallback to my OpenAI app in 10 minutes You're running a production app on OpenAI. One Tuesday morning it goes down. Your app returns 500s. You spend an hour refreshing status.openai.com. There's a better setup. Here's how to add provider fallback to any OpenAI-SDK app without rewriting anything. When you call OpenAI directly, you have one point of failure: from openai import Ope
Microsoft's 'Co-Authored-by Copilot' Tag: Unpacking the Strategic Play for AI Dominance in VS Code The persistent insertion of 'Co-Authored-by: Copilot' into commit messages within VS Code—often irrespective of GitHub Copilot's active contribution to specific changes—is far from a benign engineering detail. It represents a calculated, multi-faceted strategic maneuver by Microsoft, signaling a pr
I have a bad habit of jumping between projects. It's not a big deal. But it happens every single day. So I built rewind. rewind That's it. No setup, no IDE, no agent loop burning through tokens. Just one binary, one command, one LLM call. cargo install git-rewind GitHub: https://github.com/Chronos778/git-rewind Would love feedback — on the idea, the UX, anything. Still early days.
OpenAI revenue is still the number people reach for when they want a leaderboard. But the cleaner frame is different: Anthropic appears to be building a different kind of AI business, one centered on enterprise customers, safety positioning, and less dependence on mass-market fame. That distinction matters because public discussion keeps collapsing three separate things into one scorecard: revenue
LLM Foundry: the boring stack that makes an LLM actually useful Most AI projects are built backwards. People start with the model and only later discover they needed a memory system, semantic retrieval, tool use, tests, and a fallback plan for when one provider decides to nap for no visible reason. That is the part I care about now. LLM Foundry is the workshop around an LLM — not the model itsel