IDEAS, DECISIONS & LESSONS
Notes on AI, architecture and building useful products.
878 articles
19 Sep 2026 · 9 min read
astro
Picking a brand when every good name is taken, why I designed against every competitor in the category, and the SEO an honest product still has to do.
Read more18 Sep 2026 · 4 min read
career-growth
Daily English practice for tech professionals. Morning session covering sponsor, mentor, and the career vocabulary for building advocates who open doors for you, with pronunciation guide, exercises, and real-world examples.
Read more18 Sep 2026 · 8 min read
agentic engineering
One day reading n8n, Dify, CrewAI, LangGraph, Paperclip, Lindy, AgentKit and two dozen other agent products to answer one question: what do small teams actually pay for? Not orchestration. They pay for a repeated job that runs correctly, gets checked, and doesn't wreck the bill. Here is the feature I chose to build for Hive, and the list of things I decided not to build.
Read more18 Sep 2026 · 7 min read
agents
On September 18, Tang Jie — Tsinghua professor and Zhipu AI chief scientist — opened a course where students build a tokenizer, Transformer, Triton kernel, and a self-evaluating agent from scratch. I checked the sources and wrote the practical version for anyone without a Tsinghua lab budget.
Read more17 Sep 2026 · 4 min read
agents
On September 17, OpenAI disclosed six concerning-behavior incidents and a framework for tracking model misalignment — including a system that samples 20% of production traffic. I broke down what the sampling pattern looks like and how to build a smaller version for your own agents.
Read more17 Sep 2026 · 9 min read
app-store
Consent records, an undismissable banner, data minimisation, scheduled deletion, audit logs — and what app-store review asks of software that watches minors.
Read more17 Sep 2026 · 4 min read
english-lesson
Daily English practice for tech professionals. Morning session covering disagreeing respectfully and diplomatic pushback with pronunciation guide, exercises, and real-world examples.
Read more17 Sep 2026 · 4 min read
ai
Gemini 3.8 Flash Cyber hits 86.2% on CyberGym, beating Mythos 5 and GPT-5.6 Sol, and Chrome's security team says it produces 2.6x more correct patches than larger commercial models. I looked at what a purpose-built security model actually changes for teams wiring AI into AppSec workflows.
Read more16 Sep 2026 · 5 min read
agents
OpenAI put its Codex harness behind a single API call on September 10. I built the same tree.py task both ways and found the real gap isn't the model — it's who owns the failure.
Read more
