Fresh insights on AI-powered development
People say local LLMs are getting better for coding. I decided to test how they work in practice, with a few experiments, without investing in extra hardware. In this article, I will show tests on `google/gemma-4-e4b` and `Qwen2.5-Coder-14B-Instruct-GGUF` models.
8-minute video for Premium members. I added Kimi K3 to the previously-executed benchmark, where frontier LLMs had to fix 3 complex bugs in big open-source projects.
16-minute video for Premium members. I gave the frontier models the tasks to not generate new code, but to fix existing code in the very old open-source projects, fixing real issues reported by their users.
11-minute video for Premium members. If you want to protect from AI agent running "rm -rf" or "drop table" as a part of the prompt, this tool will help you.
17-minute video for Premium members. I tested Ponytail skill in Claude Code on three different projects and prompts, comparing the speed, token usage, and the code quality.
I've been using Claude Code for a while, so here are my personal workflow improvements that I use the most, as of June 2026.
A very simple skill that you may also use as a prompt, when you're running out of context/time in the current coding session, and you want to continue later, potentially with another agent.
If you've a React app, just tell your agent this.
Another weekly AI coding newsletter I've compiled with AI coding tutorials, news, and "tricks" from the community. Enjoy!
26-minute video for Premium members. I went through /grill-with-docs session based on a project description from a client, and then gave the result docs to Composer 2.5 to implement the code.
You'll also get two free tutorials:
Sent every Wednesday. No spam, ever. Unsubscribe anytime.