Your AI Agent Has Amnesia
In a previous post, I wrote about an AI tutoring system that generated identical verb conjugation exercises across every session — grammatically perfect, pedagogically useless. The student scored 1...
In a previous post, I wrote about an AI tutoring system that generated identical verb conjugation exercises across every session — grammatically perfect, pedagogically useless. The student scored 1...

I’d been running my AI-powered exercise generation system for weeks. It produced worksheets, rendered them to PDF, evaluated photographed handwritten answers, tracked scores, and adapted difficulty...
I asked Claude Code to design a Neovim maintenance system — update scripts, upstream sync, cross-machine portability, the works. It explored my setup in parallel with three agents, drafted a compre...
My VPN stopped connecting. Not with a helpful error message — the Alacritty terminal window spawned by my opencon command opened for a fraction of a second and closed. No output, no log, nothing to...
Our weekly meeting just ended. Gemini captured the notes automatically — attendees, topics discussed, decisions made, and a tidy list of action items at the bottom. I close the Google Meet tab, ope...
I’ve been diving into the DeepLearning.AI course “Build with Andrew”, and it gave me a profound realization. The real insight isn’t just a new way to write software—it’s that highly technical field...
Over the past weeks, I’ve tested various methods to get LLMs to produce consistent, well-structured responses—an essential step when integrating these models into programmatic solutions, where free...
My GitLab CI/CD pipeline showed “Job succeeded” for the release stage, but CHANGELOG.md never changed. The version bumped correctly, tags were created, yet the changelog remained empty. No errors a...
After merging a PR to the main branch of the crmPack R package repository, I noticed the GitHub Pages deployment workflow failed with a cryptic error: atomic push failed for ref refs/heads/gh-pages...

As a data scientist or ML practitioner, have you ever found yourself juggling multiple model experiments, losing track of which hyperparameters produced the best results, or struggling to reproduce...