Copasetic Flow

 Debug notes from getting the AI help feature of the free ham radio exams to work today. Grabbing a text answer from OpenAI still works: That's from this method async function retrieveTextWithFileSearch ({ system , user }) {   const vsId = localStorage . getItem ( 'vector_store_id' );   if (! vsId ) throw new Error ( 'No vector_store_id found.' );   answText = answText + " " + user ;   const resp = await openai ( '/responses' , {     body : {       model : 'gpt-4.1-mini' ,       input : [         { role : 'system' , content : system },         { role : 'user' ,   content : answText }       ],       tools : [{ type : 'file_search' , vector_store_ids : [ vsId ] }]     }   }); With the agent  flow, it doesn't work async function retrieveTextWithAgent ({ system , user }) {   // 0) Make sure we have ...

  This weekend I had a little extra time, so I ran a quick sanity check on the CesiumJS RF field mapping project. I pulled all the buildings out of the Python model to see if the results matched what a bare quarter-wave vertical antenna should look like on its own. It wasn’t that anything seemed wrong — I just wanted to make sure the simplest case still looked the way physics says it should. At first, he results were surprising — most of the points vanished. I fixed it. Then the field strength was highest at ground level instead of rolling off. After some debugging (and a few questions for GPT-5), the ground reflection model was corrected, and the field now looks just like the math says it should: deep null at the base, smooth roll-off to vertical, and a uniform pattern throughout. Sometimes, the most productive way forward is backward — strip the system down and see if the simplest case still holds true. All the details can be found in the video below.

 We pushed the teletype prototype for Project TouCans further today! KO6BTY transmitted a CQ call on 2 meters, and I managed to decode it—at least semi-successfully—through audio from my K6 UVK5(8). It’s not perfect yet, but it’s another good sign that Project TouCans’ RTTY experiment is working. For those that don't remember, or weren't follwing along, I started workign on the possibility of teletype using Project TouCans back in May . I didn't have the time to add a frequency change relay and possibly a different internal keyer to TouCan's Rockmite, so I settled on converting the microPython code intended for TouCans into JavaScript that could be run on the blog using GPT. It worked. I knew this right away becasue DroidRTTY decoded the audio output of the blog page app. Meanwhile, CW on 2 meters has become kinda popular lately thanks to  KI7QCF . My mind put the two topics together today, and voila! Here's a video that explains it all. The semi-successful deco...

 This blog was mentioned by GPT5 in its answer to my somewhat obsure question about special relativity! Here's the question. Yes, I did already know the answer, I was just taking GPT5 as a research tool out for a spin after reading Simon Willison's GPT-5 aka Research Goblin  post . The answers it came back with were spot on. They highlighted Kerapatoff's involvement which I find particiularly interesting. Then, when I scrolled, (very far down), it's cited sources, I saw... in the 'More' section... As it turns out, the 'More' panel was intended as a 'You might find this intereseting' sort of thing. So, it's cool to see the blog on GPT-5, but GPT-5 didn't actually use the blog. AI and its sourciness (to coin a term) have come up a recently on the SolderSmoke blog. OK, off to listen to some recorded QSOs!

 GPT5 helped me understand how the Tuna Topper ][ amplifier in Project TouCans operates yesterday. It started from just this clip of the schematic! While debugging the power supply relay of Project TouCans a few days ago, I noticed an interesting thing. With the Pico-W rig controller plugged into the supply brick TouCans itself was only being doled out twelve volts by the phone charging brick in its base, not the fifteen volts its USB-C adapter was asking for. That mattered the most to the Tuna Topper II  amplifier that drives the five watts to the antenna. I changed the rig so that, for now,  the Pico-W runs on three AA batteries. That upped the supplly to the rig back to its intended fifteen volts. I wanted to understand in broad terms what that meant for the power output of the rig. I tooled around for a bit on paper and spreadsheets before it occurred to me to ask GPT5. I didn't expect to get an answer at all. I definitely didn't expect it to be able to read the sc...

 Early Sunday morning, the code generated by ChatGPT became noticeably clunky. Why!? I figured it out when this message arrived Ah yes! The LLM that berates me a bit for the code it wrote :) At some point after the release of GPT5, OpenAI started defaulting my chats back to 4o. For me GPT5 is better. I switched back over 5 and a bit later, the code coming out of the LLM was just working, and when it didn't, I got messages like this By the way, at that point GPT5 was fixing code created by 4o when I had specifically asked for: " Also save the vh and vw settings of the subpanel in subpanelsize and resize it to its original extent if the subpanelsize arg is present in a url  " Anyway! GPT5 rocks for me. If you're using the browser UI instead of the API, check to see what model you're using before you go too far down the wrong path.

 I'm using the new map in map feature I coded up this week to for a map that demonstrates that as the sun sets in Sweden, it's rising near Las Cruces, NM. A few minutes later, my QSO to Sweden from the Organ Mountains went through. The code is in a github repo . Here's the map: And here's a video demonstrating how to interact with the map above: For those who are curious, here's how Project TouCans was situated that day. Note that the dipole is only about five feet off the ground.

 I frequently find myself zooming in and out of QSO maps to see where the sun was with regard to my station's horizon  vs how far a given QSO propagated. I wanted a way to view maps without all the zooming. Now I have it! How I got It I've had Cesium maps on the blog for a while. Once I got the idea for a better way to view QSO maps, I deliberately executed on the habit I've been trying to build in myself:  I immediately asked GPT5 if it could augment my existing code. It turned out that it definitely could. In under half an hour, I had the new map view pictured above. You can steer around the maps at my POTA post .  The code for implementing map in map can be found in the csm-map-n-map repo.

 Project TouCans made it back on the HF airwaves last night! I had forgotten that urban POTAs are kind the epitome of luxury here in San Francisco. On my way to the bus stop for the MUNI 49, I noticed that it was happy hour, so I stepped in for a drink. Perched on a barstool at the joint's open front window, I contemplated the world outside and whether or not the radio would work. The power switch latching relay for the rig gave up on the last day of our Great Basin National Park camping trip. That'd been perfect timing, (if the thing was going to break at all), but also led to me not being on the air in the better part of two months. I wound up making the ten QSOs to activate the park in just over half an hour. My operating site was on the campus of City College San Francisco (CCSF.) The view across the city is kind of nice. I was there just into the night this time, and the city lights up after dark. I'm trying something new in the map below. I asked GTP5 to help me with...

 This week's AI project is to create an AI Morse code decoder. I've been working with the new ChatGPT 5 model since late last week. I've asked a few different models if they could understand Morse code. ChatGPT 5 couldn't. Gemini couldn't. That's when it occurred to me that this was probably the perfect time to learn how to use TensorFlow to make an AI. So, I changed my question. I asked ChatGPT 5, "If I wanted to setup a model that learned Morse code using Google's Tensor engines, could you describe the entire process and output the code for me?" To which it promptly, (what an awesome pun!), replied, "Heck yes—that’s a super fun project. Here’s a complete, practical path to a TPU-accelerated Morse code recognizer using TensorFlow + CTC (Connectionist Temporal Classification). It generates synthetic Morse audio (with realistic timing/noise/tempo wobble), trains a small CRNN on log-mel spectrograms, and decodes with greedy CTC. You can run it ...

 I've been looking for an excuse to try parallel processing with Python for a few months and yesterday, the FBI provided one. They released a collection of records related to the assassination of Reverend Dr. Martin Luthor King Jr. It's easy enough to get a count of the pdf files released from the announcement page . Information about the files released to the National Archives I was able to quickly read that there were 6,301 files. A brief internet search indicated that the files have not been released in any kind of compressed container, like a zip file yet. I also tested that the search box only searches the pdf file names, not their contents. The immediate next question was how many bytes of disc space do all the pdfs consume? I asked Chat GPT o4-mini-high to write a Python script to determine the size of the all the files combined. The script was unable to determine the size of each file by looking at the HEAD of the URL for each file, so it wound up having to use GET req...