I spend a lot of time preaching architecture and constraints, so it is always nice when a side project gives me receipts. Adding this new feature to DumbQuestion.ai was a good reminder that a well-structured first version lets you spend your next ite...

Google has officially replaced Gemini CLI with the new Antigravity CLIhttps://developers.googleblog.com/an-important-update-transitioning-gemini-cli-to-antigravity-cli/ and launched it alongside Gemini 3.5 Flash, which became the default model for th...

Google has officially replaced Gemini CLI with the new Antigravity CLIhttps://developers.googleblog.com/an-important-update-transitioning-gemini-cli-to-antigravity-cli/ and launched it alongside Gemini 3.5 Flash, which became the default model for th...

Is a $20/month Google AI Pro account worth it versus running Gemma 4 31B on OpenRouter pay-as-you-go? This Ship-Bench run was designed to answer that question across a realistic coding workflow rather than a single coding prompt. Hypothesis: Gemini'...

When organizations introduce AI, they often make a critical error: they create entirely new metrics to measure its impact. This approach misses the fundamental truth that AI is a tool to help achieve existing goals, not a reason to change what succes...

Why maintaining a healthy skepticism gets you better outcomes. One of my old hobbies was writing for independent music magazines, such as Spill Magazine distributed free at music venues and DV8 distributed free at hair salons. Over the years, I saw ...

https://www.kasetto.dev https://github.com/pivoshenko/kasetto Hey community! I want to share an open-source tool I built for myself, and that I hope will be useful to other developers working with AI agents. The Problem The more AI coding tool...

There’s a specific kind of anxiety that hits at 11 PM when you’re scrolling through someone’s thread about the AI workflow that supposedly changed everything. You were productive today. You shipped code. But now you’re wondering if the way you shippe...

Developers face a real choice: pick a coding model or agent based on synthetic benchmarks that look great but do not predict actual project work. The problem is no longer whether models can score well on those benchmarks; it's whether those scores st...

https://www.kasetto.dev https://github.com/pivoshenko/kasetto Hey community! I want to share an open-source tool I built for myself, and that I hope will be useful to other developers working with AI agents. The Problem The more AI coding tool...

A few weeks ago, I wrote about The Review Bottleneck — how AI-generated code comes with so much confident explanation that we’ve stopped actually reviewing it. We’re not doing more engineering. We’re doing more trusting. The respons...

I've been working on human+AI collaboration for years. That part I mostly figured outhttps://paice.work. The part that kept breaking was getting two AI agents to truly collaborate with each other. Every orchestrator framework I tried had the same sh...

A leaderboard for DumbQuestion.aihttps://dumbquestion.ai/?utmsource=legion sounds simple. Track the most asked questions, display them. Done. Except people never ask the same question the same way twice. I was curious about how creative users of Dum...