Notes on AI, tools, and tech.
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
I gave Codex full access to my machine for one afternoon. It deleted about 300GB of files from my C and D drives. This happened to a user on X last week. They wanted to use up their Codex credits before a reset, so they asked the agent to remotely verify their project scripts and … Read more
I’ve been using AI coding assistants for a while now. I started with Trae, specifically its SOLO mode. It felt like the WebStorm of AI editors. Everything worked out of the box, and I never had to think about how to talk to it. It just understood me. Then I switched to Claude Code. And … Read more
The hype around Prime Agent is getting ridiculous. People are calling it the next step toward AGI. Some claim that with Opus 5 it scores 95.5 percent on ARC-AGI-3, beating the human expert baseline of 95.4 percent. That is a big number. But I kept reading the same talking points everywhere, RLM, Continual Harness, prompt-as-a-variable, … Read more