Codeminer42's Engineering Blog
LLM
Your AI Skills Setup Is Probably Wrong
I ran 51 multi-turn evals across 4 configurations and read Claude Code's source. Skills and CLAUDE.md are both just prompt. The difference is whether the prompt reaches the model.
Why a 1990s Machine Learning Algorithm Destroys LLMs at Predicting House Prices
I asked an LLM how much my neighbor's house might be worth, a 300m² place with 4 bedrooms, not too old. It gave me a vague, hedged answer that could…
[Dev Weekly #97] Astro is 39% More Loved Than Next.js, Claude 4.6 + GPT-5.3 Codex Just Dropped, and more
HELLO EVERYONE!!! It’s February 6th 2026, and you are reading the 97th edition of Codeminer42’s tech news report. Let’s check out what the tech world showed us this week! The…
Powering Your Database Queries with a LLMs and MCPs
Today, we live in an era where we increasingly encounter AIs of various types and uses in our lives, whether due to hype or not, such as the well-known ChatGPT,…
Setting Up A Free Claude-Like Assistant With OpenCode And Ollama
I've been experimenting with Claude Code for a while, and there is no doubt that it's a powerful assistant, capable of performing many tasks as a coding partner. While it's…
