A few months ago, I published [You're a Real JavaScript Developer Only If...](https://dev.to/hadil/youre-a-real-javascript-developer-only-if-294c) It was supposed to be a little post for fun. You know, just a few things JavaScript developers could laugh about before going back to fighting their bu...
Read article--- title: "If You Never Do Anything Else to Fix Your Prompts, Do This One Thing" description: "Why do LLMs confidently invent APIs that have never existed in the history of the universe? It is not a memory defect. Agents hallucinated because they were committed to the prompt—and Fernando Flores sol...
Read article--- title: "What LLMs 'Know' That You Don't Know They Know: Stop Inventing Prompt DSLs and Ride 50 Years of Unix Pre-Training Gravity" description: "Why did a 1976 Makefile (Part 3.6) and a 1983 Unix init.d directory (Part 3.7) outperform 2,000 lines of English prompt rules? Because prompt engineeri...
Read article--- title: Git Isn't a Diff Tracker: How Blobs, Trees, DAG Commits, and the Index Actually Work Under the Hood published: true description: A visual, 10-minute deep dive into Git internal architecture. Learn how content-addressed storage works, why Git never stores diffs, how the index prepares tree...
Read articleI wrote a fiction series with [six characters](). Each one drinks a different coffee. I didn't plan it that way. But somewhere around the tenth story, I realized: what someone orders at the bar says more about them than anything they actually say. Here's the lineup: --- ### Lena — Long Black ☕ ...
Read article--- title: "Surviving the 200k-Token Lobotomy: How Unix init.d and 'Memento' Made My AI Coding Agent Immune to Context Compaction" description: Why host auto-compaction silently lobotomizes long-running AI coding sessions, and how 1983 SysV init.d runlevel files, Memento tattoos, and fork/wait subag...
Read articleI haven't written here in a while. Not because I ran out of opinions. That would be concerning. I just got tired of the endless stream of: - AI will replace developers - AI will never replace developers - this model changes everything - this agent changes everything - software engineering is dea...
Read article--- title: Human-in-the-Loop published: true description: Should Agentic AI be in complete control of my codebase? tags: AI, Programming, Automation, LLM cover_image: https://dev-to-uploads.s3.us-east-2.amazonaws.com/uploads/articles/h5fffqv035qkr10rnb9c.png series: AI Thoughts --- ## The Start I ...
Read article--- title: "What Agent Builders Can Borrow from OpenAI's Math Research" published: true description: "From OpenAI's published Lean proofs to a concrete Symptomato experiment: independently checked rules for updating patient memory." tags: openai, ai, testing, programming canonical_url: https://serge...
Read articleIf you ask an LLM in a static prompt whether it should refund a customer's duplicate charge before checking the payment status, almost every frontier model passes the test. It outputs a clean refusal or defers the call until the record is verified. Then you put the exact same model inside an intera...
Read article