Notes on AI, tools, and tech.
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. … 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 … Read more
I’ve been using AI coding assistants for a while now. Not because I can’t write code without them — I can. But because they save me time. And time is the one thing I never have enough of. I started with Cursor. Then I tried Trae. Then Claude Code showed up and everyone lost their … Read more
I’ve been using OpenCode for about six months now. Started out just treating it like a chat box. Took a while to figure out what actually works. The default mode is Build. You say something, it starts changing code. Problem is, most of the time I don’t know exactly what I want yet. So I … Read more
Google just announced they’re killing three Gmail features that a lot of people rely on. Starting January 2027, you won’t be able to send emails from a Yahoo or Outlook address through your Gmail account anymore. The web version of POP fetching is going away too. And Gmailify—the thing that lets Gmail’s spam filters work … 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. … 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% on ARC-AGI-3, beating the human expert baseline of 95.4%. That’s a big number. But I kept reading the same talking points everywhere — “RLM,” “Continual Harness,” “prompt-as-a-variable” — and … Read more