LLM

This is a small framework I put together to generate YARA-L detection rules with an LLM in a self-correcting feedback loop. It aims at automating Detection Engineering for Google SecOps (Chronicle)

This post shows the minimal proof of concept SSH tool I built for Opencode AI, and how it could be used to “talk to” remote machines.

I used AI to learn Golang in 2025. I was faster than ever, but couldn’t remember what I’d written. A recent MIT study explains why.

Useful ways to leverage Termbot as a Linux CLI LLM tool. From piping/redirecting stdout to reading text from local files, it allows for several combinations of “data chaining”

Weaver is a tool I made for extracting saved acticles from pocket , with a specific tag, and summarize them with OpenAI GPT-4. This way I can save blog posts, documentation, etc. And periodically use Weaver to extract summaries of all of them at once.

Termbot is a command-line interface tool for conveniently interacting with OpenAI’s GPT-X or Groq’s natural language processing system, directly from your terminal. It allows the user to use standard ChatGPT-like question/answer functionality, with added flexibility such as interacting with local file contents, sending large data from STDIN, using custom local instructions, and more.