One article at a time.
Google keeps shipping AI features that look great in a keynote and then quietly disappear from my life. So when Chrome started baking Gemini straight into the browser, I assumed Auto Browse would be another one of those. Then I read the fine print. This isn’t a summarize-the-page button — it’s an agent that can … Read more
I’ve been using GitHub Copilot for about a year now. It’s good. Really good. But not everyone wants to pay $10 a month for autocomplete. Some people code once a week. Some are students. Some just want to see if AI-assisted coding actually helps them before committing to a subscription. So I spent the last … Read more
The short version: DeepSeek open-sourced their Agent harness, the scaffolding that turns a raw model into something that actually works in the real world. And they did it in a way that openly admits what everyone in the industry has been quietly realizing: the model itself isn’t the whole story anymore. Honestly? I spent the … Read more
Google dropped Gemini 3.7 Flash on August 13. That’s three weeks after 3.6 Flash came out. Three weeks. I had to double-check that date the first time I saw it. Here’s what actually matters: it’s better at coding, better with AI agents, and it costs half of what 3.6 Flash originally cost. That last part … Read more
Microsoft started rolling out the unified Copilot app yesterday, August 14. If you’re using Copilot right now—either the consumer version or the Microsoft 365 one—things are about to look different. Not different in a huge way, though. Let me explain. The wider hype around AI coding has cooled off anyway. Vibe coding getting boring is … Read more
I’ll be honest: I had high hopes for DeepSeek Harness. When I heard DeepSeek was releasing their first Agent product, I pictured something like Codex or Workbuddy. Maybe a polished desktop app. Or at least a Claude Code-style CLI tool that you could fire up and start using right away. I thought the whole point … Read more
DeepSeek dropped something new just yesterday, August 13. Not a model this time, but an agent harness called DeepSeek Harness. They open-sourced it under MIT and put it up on GitHub (https://github.com/deepseek-ai/deepseek-harness). I spun it up last night and spent a few hours with it. Here’s what I found. Wait, I should back up. What’s … Read more
Honestly? I didn’t see this coming. DeepSeek has been killing it on the model side for a while now. Cheap API, solid performance, open weights. They’ve been the budget champ for developers who don’t want to burn cash on OpenAI or Claude. But yesterday they dropped something different. Not a model. Not a price cut. … Read more
I have been using OpenCode for about six months now. I started out just treating it like a chat box. It took a while to figure out what actually works. The default mode is Build. You say something, and it starts changing code. The problem is, most of the time I do not know exactly … Read more
I’ve been watching the Vibe Coding hype cycle play out for over a year now, and honestly? I’m relieved it’s fading. When it first dropped, my feed was flooded with “AI coding is the new era” posts. People were building full websites without writing a single line of code. Non-programmers shipped apps in two hours. … Read more