Blog

A few months ago I rushed to adopt new harness by Twigpine (Gitlawb by that time). It looked like a solid foundation for improving my independance and flexibility with LLM tools. Claude Code had, and still has, some great features. But I never expect proprietary harness to unleash the full potential with 3rd party models. I wanted something I could own, extend, and adapt as the AI ecosystem evolved. I've been touching the topic of agentic development from a different angle recently. Agentic De

The LLM (AI) hype became disruptive. While frontier labs as Claude and OpenAI has been racing for providing better harnesses an entire market of open source harnesses grew from up. Now most of the provider and LLM aggregators (providers who resells you access to LLM) are building own harnesses as well. This race gives us some clues: 1. There are leaders in the race, there are no winners in the race 2. Providers are fighting for the attention. It's not enough to provide access to models. A mo

Your tech stack isn’t just a collection of technologies. It shapes how you think, what you can build, and which opportunities you can pursue. Popularity doesn’t guarantee suitability, and AI doesn’t replace understanding. Choose your stack for tomorrow, not just today.

My brother called on Friday morning. I’ve been busy and rescheduled the conversation. And since my plans went exceptionally well, I reached him back a couple of hours later. What I heard in the next 30 minutes changed my plans for the rest of the day and upcoming weekend. And I must confess: I did that. I’ve been vibe-coding for many hours. And that’s a mix of feelings, yet I can’t say I’m disgusted, and I’m not in love like I used to be. Probably that’s the most beautiful part. It’s just ano

Sending API requests is simple and available out of the box. Until data must not be sent outside. We either not use LLMs or accept the costs of running LLMs on premise. Sometimes it might be just a few hundreds away.