AI
Stale docs are prompt injection you wrote yourself
An agent opens a file, sees a strange-looking loop, and "simplifies" it. The loop was strange on purpose. Someone had chosen it months earlier, after an incident, in…
Posts
- AI
Six weeks of AI code review: what it caught and what it let through
The comment started with three words: This breaks prod. It was a PR of about five hundred lines -- in a repo I had just encountered, and I…
- Dev Weekly
[Dev Weekly #125] Qwen 27B Runs Locally and Crushes Benchmarks | Supply Chain Under Siege | DuckDB 2.0 Reshapes Analytics
HELLO EVERYONE!!! It's August 20th, 2026, and you are reading the 125th edition of Codeminer42's tech news report. Let's check out what the tech world showed us this…
- AI
I built an AI agent for our World Cup betting pool. She beat all of us.
Memory and context engineering for a long-running AI agent: how BETanIA got a diary, a mood, grudges, and a compaction strategy - and won our World Cup pool.
- Dev Weekly
[Dev Weekly #114] Google’s Gemma 4 Changes the Game | Ruby Performance Secrets Exposed | Trust Over Velocity
HELLO EVERYONE!!! It's June 5th, 2026, and you are reading the 114th edition of Codeminer42's tech news report. Let's check out what the tech world showed us this…
- AI
How Far Can AI Self-Validate Rails Code?
A few weeks ago, I wrote Stop Reading AI Code, Start Measuring It: A Rails Playbook. The idea there was that if you stop hand-reviewing every line of…
