Copasetic Flow

  Do LLMs always generate the correct set of code given their inputs? Nope. You can use the same LLM to verifiy its own outputs if we're clever about it though. Here's an example from a recent HF interference model I asked GPT-5 to build for me after a Parks on the Air (POTA) ham radio outing in downtown San Francisco.  My first QSO perched on the edge of One Maritime Plaza was with AL7KC. That's not too surprising, I pretty regularly communicate with AL7KC. Except. It was kinda surprising because there was a skyscraper—Gateway Vista West—directly across the street between me and Alaska and about twenty-three meters away. View from the QTH That one little skyscraper led to a lot of fun HF propagation analysis using GPT-5. I described the area around my transmit site at One Maritime Plaza to GPT-5. I got some really interesting interference patterns based on the surrou...

 This week I spent some time tightening up the workflow for comparing F2 ionospheric data across different POTA outings. It turns out documentation really does matter. By writing things down, I’ve not only made the manual process clearer but also pushed the automated flow forward. With GPT-5’s help on documenting proton and electron flux plots, and my own notes on numeric F2 graphs along QSO paths, the project is steadily becoming easier to repeat and share. I put in a little bit of time working on being able to easily compare F2 data for different POTA outings this morning. It turns out documentation really does matter, so I've been focusing a bit more on it. I have a number of tools that allowed me to pull in F2 data quickly. This week I've been trying to spend time pulling them into an automated flow. As I've implemented this flow, I've discovered that I haven't taken the time to document the tools I've already built.  I asked GPT5 to document the solar prot...