Copasetic Flow

 I'm condensing the steps to move from travel manifest page to human readable findings to sqlite database here. History Research Contextual Recap I'm working on a history of physics research project, The Gladych Files , that explores how industrialists interested in fringe physics wound up actually funding mainstream general relativity research. As part of that research, I've been looking at the travel manifests of various industrialists and research scientists from the 1930s to the 1950s. Because there are literally thousands of passengers on their combined voyages, I'm using LLM agents orchestrated through Gas Town to coordinate the research. At present, I am working on a bit of a mystery. Multiple sources state that Hedy Lamarr came to the United States aboard the S.S. Normandy, arriving on September 30th, 1937. That's the same ship that Tom Slick, (one of the industrialists of whom I spoke above), took across the Atlantic. There's only one problem. Hedy is...

 I haven't mentioned my portfolio site here before, but I did manage to fix page view tracking on it today, so that's kind of nice. It was the final project for a digital portfolio  class I took at City College San Francisco and highly recommend. History Research Recap I'm offloading a significant amount of research work for my history of physics book, The Gladych Files , onto an orchestrated platform of LLM agents in Gas Town . The bulk of the work is to research passengers on trips the main characters of the book took from the 1930s to the 1950s. One of the main subjects of the book is Tom Slick . While returning from a trip to attempt to spot the Lochness Monster while he was a student at Yale—seriously, I love this book—he was aboard a ship, the Normandie, with Hedy Lamarr. The ship also had over 1,000 other passengers including the grandchildren of Henri Matisse . My  agentic AI research team comes to task because it's not a small project to research each of a t...

 Moving the camera to see the sky in CesiumJS maps has always been a little bit difficult for me. So,m when CesiumJS announced their baseline MCP for controlling the camera on CesiumJS maps, I leaped at the chance to try out an MCP and to grab hold of better control of my map camera.  This week, the sujbect of eclipses came up in my Gladych Files research. ( Ferry Barrows Colton , famed National Geographic Science writer of the 1940s was part of the 1947 Brazil eclipse expedtiion, and was also on board the Normandie with Tom Slick in 1937.) That reminded me of the following picture I took of the 2017 eclipse from Wyoming.  I've wanted to identify the stars on that picture for years, so I was curious if CesiumJS had accurate constellation maps for a given date and time. Turns out, they do. But, how to look at the stars? I revived my version of the  MCP camera control server for CesiumJS in a few minutes by starting Codex in the repo directory on my local machine, a...

 It was fun getting to use Anthropic's Fable-5 for a few days. Hopefully the chance will come up again. For the moment, the US government has denied access to non-US citizens.

 With all the work that's been put into making agents "correct" by construction, I gotta say, sometimes I need an LLM agent to take a chance at just being wrong. I'm working on a book project called The Gladych Files . While the book is narrative nonfiction about the history of general relativity research, it explores the liminal space inhabited by very rich fringe scientist speculators of the 1950s who funded mainstream general relativity advances, (more or less on accident.) In those spaces, you'll find Tesla, the architect of the FBI building, Timothy Leary's LSD explorations and many,  many other things, institutions, and people.  I've accumulated hundreds of pages of historical documents from various archives, and I'm using orchestrated agentic AI, (in the form of Gastown), to review those documents. So far, the analysis has gone well, but last week I saw something that made me look up. I'd accidentally input the same archive page twice, so i...

I started my lab book entries when I was a physics graduate student. It's kind of amusing and kind of cool how far I've come. I have the equivalent of a grad student, (aka Claude Opus 4.7), working for me now. I spent some time over the weekend setting up an OCR framework for a book research project of mine. I've been coming up to speed on evals, so I decided to run one to determine which model was the most accurate and cost effective for doing OCR on travel manifest pages. I stepped the eval along rather than automating it and talked the results through with Opus as I went.  First, it turns out that Opus at low effort is the most accurate and the most cost effective choice! That was a surprise. The result has to do with Opus' ability to look at higher res images which means it needs to think less for OCR vs. Sonnet. Second, at the end of the eval, as I was preparing to write up my results it occurred to me that I could ask my grad student to do it instead. Here's...

 I took time to play with a new Dolt enabled app example called Quorum last night. Quorum sets 13 LLM agents with different defined personas  loose on a users question. The agents come up with solutions to the question and then discuss their individual solutions with each other to arrive at a consensus. There's much more detail in this blog post that accompanies the app. Quorum is cool. It is not, however, what I wanted to talk aobut here. Instead, I'm going to focus on the blog post for the app. In short, I'm very excited to see ideas that I've used to manage verification processes for years get codified into tools for LLM agents. Here's one of the important parts " I can shut down the app, lose the server, or disappear entirely — and the deliberation history remains, publicly accessible and cryptographically verified. " Imagine what an engineer can do to work back through their debug hypothesis tree with that sort of infrastructure! As the article'...

 I asked ChatGPT 5.4 Thinking to write some JSON-LD text to summarize a blog post this morning along with alt text for the posts images and got this When I asked it to file a but report on itself, I didn't really expect it to succeed, but I didn't expect more oaicite index listings for the proposed issue description. (Kinda obviously, I also haven't had enough coffee yet :) Anyone else seeing this? Happenings of Interest   (radio and nature) Where was our skip zone at San Bruno? For example. QSO Log Table containing QSOs in text Callsign rx RST tx RST Time (GMT) Frequency KBTEST 539 559 16:42 14058.3 kHz (Add callsigns as post tags?) Unschooling Highlights POTA tx QSL: QSL rx album: References POTA ( Parks on the Air ) Local Ionograms https://lgdc.uml.edu/common/DIDBYearListForStation?ursiCode=PA836 (for example) Videos Demo

  Just a quick note that the AI tutored Project TouCans exams are up and running for the latest US technician class question pool for the license exam.  The exam sprang out of two different projects here at the home QTH. KO6BTY is studying for her extra class license. Also, I'm learning about developing code with AI. And voila: AI tutored ham radio practice exams. Try the AI-tutored Technician Class practice exam now. Project TouCans technician class practice exams . Read more about this project: First  demo  of OpenAI ChatKit enabled exams First release of extra class exam based on OpenAI responses API Removing the vector store  to reduce costs Experiences with Vector Stores Early debug to add contexts by local compute and storage First release of extra class exam  with no AI

 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 ...