Copasetic Flow

 This... is interesting. The oldest kid here is taking Calc III, The Calculus of Multiple Variables. There's a whole thing every week where she winds up spending a lot of time transcribing her homework into a more readable form so that she can turn in her work on the assignment's due date. I wondered if an LLM could help with that. I tried out ChatGPT 5.3 with this picture to start. Believe it or not, this contians two homework problem, (and, accidentally, my foot.) I asked  "Please write these two math solutions as laTeX and write them to a pdf file." I wasn't too surprised when it replied with  --------- "I only have one photo so far, and parts of it are too hard to read reliably to typeset without guessing. From the visible top portion, I can make out a problem that looks like T ( x , y ) = 60 1 + x 2 + y 2 T(x,y)=\frac{60}{1+x^2+y^2} T ( x , y ) = 1 + x 2 + y 2 60 ​ with partial derivatives like ∂ T ∂ x = − 120 x ( 1 + x 2 + y 2 ) 2 , ∂ T ∂ y = − 120...

 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 brief note to mention that when I was fighting Codex CLI earlier this week to call the OpenAI Whisper API , what was really going on was that Codex CLI was sandboxed. ChatGPT helped me modify the script I was creating so that the script itself punched through the sandbox by clearing the proxies that had been setup to keep Codex CLI in the secondbox. It's interesting that ChatGPT didn't just tell me to add the --yolo argument to my codex cli command line. I wonder if that's part of its guardrails, or if ChatGPT doesn't know about the arguments to Codex CLI yet through training. I saw similar things happen when  ChatKit was announced. ChatGPT wasn't quite sure what it was on the day of the announcement. The good new is that I'm now calling APIs without any shenanigans because I learned to simply add '--yolo' the following day. That argument comes with its own set of risks, but I'm ok with those for the moment.

I put OpenAI’s gpt-5-nano and gpt-5.1 head-to-head on my psy-ops article scorer to see what you really get for the extra spend. Along the way I ran into pricing surprises, wild variance, and a reminder that ChatGPT’s shiny new memory feature can quietly bend your evals if you’re not careful.   A post on LinkedIn a few days back suggested using Small Language Models (SLMs) as opposed to LLMs for repetitive tasks. This seemed like a great idea in some regards for me, but I was curious about how it would apply to apps that were intended to perform lanugage analysis. Luckily, I have the psy-ops app up and running. Also? At the moment, it is using a close-to-an-SLM model, gpt-5-nano due to pricing decisions. I used it as a test vehicle to look at the difference betwween gpt-5 nano and full featured gpt-5.1. The testing framework I used: Starting from this article, I first did three separate anayses with gpt-5-nano, and then three others with gpt-5.1. I then used gpt-5.1...

  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

 I’ve just launched the new Extra Class Practice Exam site, and it’s officially the first app running on the new Project TouCans platform! The exams follow the same familiar format as the ones here on the blog — but with a major upgrade. Now, when you’re stuck on a question, you can click “AI Help” to start a ChatGPT-powered tutoring session for that specific problem. You can try the exams here: 👉 https://projecttoucans.com/

 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 ...