I've been playing wit ionosphere maps and Cesium's MCP controller this week. I wanted to try some quick experiments, but quickly realized I hadn't learned how to hooik connect the Cesium Sandcastle to the their MCP as a client . The method Codex Sol 5.6 and I finally devised and successfully used is documented below the video. Using that method, I was able to set up the following ionosphere…
Fun with superconductors on a Monday morning. Did you know that Type II superconductors like the YBCO one shown below can pin magnetic flux? Consequently, if you freeze in the field lines, you've got a superconductor that behaves like a magnet.
I'm still seeing Sonnet fan work out beyond its model capablities using subagents. You can see in the window below that the Gas Town polecat has had to stop and compact its context before proceeding. The good news is that when these subagent work fans don't turn into storms, I'm seeing more thorough reseearch findings returned. The bad news is that with Sonnet's limited context, those findings…
This is kind of cool! I started a new project today using codex --yolo, (I didn't want to use my Claude tokens until I'd worked out the design and architecture a bit more.) When I got done coding with codex, I asked it to create a repo for the work we did. That seemed to work, but I wanted to verify that the repo was ok, so I typed gt status and was immediately presented with I answered y and the…
Just noting a feeling, nothing quantitative, but I think I've noticed that if more Claude agents are working at once, they each tend to create fewer subagents. If that's true, and it's a big if, I wonder if there's something at Anthropic that trottles or budgets overall effort to an account. Just to be clear, I've also watched five polecats descend into a complete and utter subagent storm like…
I've seen a few posts in the last week that talk about engineer's loosing their time to think because they're too busy watching what their LLM agents are doing. Anthropic's models, even under GasTown, have decide to spontaneously fork and find other ways to farm work out to subagents, occasionally causing agent storms on my project in the last week, so I can sympathize a bit more now that I did at…
Working with Fable last week, I noticed that it can get very excited about fanning out tasks, (to the point of crashing my WSL session.) I experimented with prompting agents to split out tasks on their own, but haven't found a successful to do this yet. Consequnetly, I reverted back to my original prompt which does not explicitly call for task splits. Then, this morning, running on Sonnet 4.6,…
Cooper95 Incident Report — 11 July 2026 (v1.13) Fable-5 Agent and Subagent Research Tasks and How to Evaluate Them Root-session reconstruction, eleven descendant transcripts, nine fork manifests, and eight timestamped screen captures. host Cooper95 (WSL2 guest) · project bg_trav · worker rust · root session 28797a95… Claude Code v2.1.207 · cwd /home/hcarter/gt/bg_trav/polecats/rust/bg_trav report…
I'm still tracking down what makes some agents find a Nikola Tesla research finding and why others do not. Today, that's led me into investigating Claude CLI's forking harness. A few notes from me. Forking looks pretty spectacular! The agent kicks off a subagent that automatically has a copy of the parent's context. The subagent doesn't add to the parent's context until it's done. So, it seems to…
More instances of variance in research results, this time around Isidore Nobel. Also, saving tokens by keeping conversations short. Missing Isidore Nobel This was probably due to a misspelling on the British manifest of Nobel's last name as Noble. The U.S. manifest has it as Nobel. Another midweek usage reset I would say this was caused by the introduction of fable yesterday, but my usage numbers…
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…
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…
Moving the camera to see the sky in CesiumJS maps has always been a little bit difficult for me. So, 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 subject of eclipses came up in my Gladych Files research. ( Ferry Barrows Colton , famed National…
Thijs is new prior to today, usage was broken out between Sonnet and other models like this It's unclear ot me if I tripped a flag somewhere as I approached my weekly limit, or this dialog is reflective of a new Anthropic usage report. I switched Gas Town over to all Sonnet models a few weeks ago for two reasons. First, to get more usage per week. Second, I've found that for the creative research…
While doing research for a book I'm working on, The Gladych Files , I wondered into the weeds of statistical analysis of LLM AI agent performance which relates to my everyday sort of work in engineering. One of the things I really enjoy about The Gladych Files, however, is that it's never long before the project pulls me back towards ham radio. The statistical analysis project involved determining…
I'm working through a methodology to study the behavior of teams of agents via observation of real-world tasks. As usual with LLMs, the concept of repeatable results is squishy, especially as compared to non-LLM deterministic computing. My finding last week was that LLM agents, especially Claude (per Google's research), can exhibit stigmergic , (a fancy word for how insects, like ants, 'learn'…
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.
Recap During an analysis of a travel manifest, two agents, (referred to as polecats in Gastown terminology), were accidentally handed the same manifest page for input. The agents produced different results. One agent found an association between Lucia Hobson and Nikola Tesla, a very valuable association for the research project. The other agent did not. A set of eval experiments ensued to…
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…
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…
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,…
I'm working through McConnell's tensor textbook, the one I used in general relativity class at New Mexico State. I'm probably not going to be looking at spacetime a whole lot this time as I'm more interested in machine learning model implementations this time. The first video in the series is shown below. Each video has a link to the next part in the series. You can find the textbook on the…
You can now play the CW Simon game on your desktop with your own iambic paddles and a Halikey Serial . (We hope to have support for Halikey Midi soon.) I was a little worried that the serial version of the Halikey was going away , but I'm super-psyched to see that it's back! I'm still pretty psyched about phone keying, so expect to see more features there, and maybe some hardware as we move…
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…
On Tuesday, I mentioned that I'd be adding Halikey as an iambic keyer to the CWSimon game. Iambic keying enabled by Halikey is something I've been meaning to do for a while, but each time I start, I realize I'm going to need to start with serial port signal inspections, and set the project back aside. This is the exact sort of thing vibe coding is good for, pushing through the parts of projects…