Filter by tag
Posts tagged with "technical"
A guide to how I added commenting to this blog with Giscus.
I went looking for a digital photo frame and found a Lenovo tablet at the same price. Here's how I turned it into an always-on home display, with a WebView launcher you can use yourself.
What we learned building a model router for a multi-model AI chat app - the scoring approach that didn't scale, and the classifier rewrite that fixed it.
How we built human-like memory for AI using Ebbinghaus decay curves, spaced repetition, and associative linking — and why forgetting matters.
Your LLM can fail silently. No crash, no error - just worse answers reaching users while your logs show 200 OK. That's one of several ways LLMOps breaks from traditional MLOps. Here's what actually changes when your model is an API call.
Git version 2.34.0+ supports SSH for signing commits for a simpler, smoother process. In this article, I've put together a quick and easy guide on how to use SSH to sign your Git commits—easy setup, secure commits, no fuss.
When an AI agent stops to ask you something, it's usually not a reasoning failure. It's a context-access failure. The fix isn't a smarter model. It's better systems for capturing the judgment trapped in your head.
A list of some useful (and potentially useful) tools that I use or might use in development projects
Research shows agent context files reduce task success rates. Here's what to do instead.
A benchmark tested 72 AI models on nonsense detection. ChatGPT's default pushes back 27% of the time. Gemini on Android? 10%. This matters when billions use AI for health advice.