Copasetic Flow

Antrhopic's Haiku model can routinely pass—about 300 times so far--the extra class US ham exam based solely on what's contained in its model.

The answer is very much, yes!

I've been playing wit ionosphere maps and Cesium's MCP controller this week.

Fun with superconductors on a Monday morning.

I'm still seeing Sonnet fan work out beyond its model capablities using subagents.

This is kind of cool!

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.

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.

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.)

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…

I'm still tracking down what makes some agents find a Nikola Tesla research finding and why others do not.

More instances of variance in research results, this time around Isidore Nobel.

I'm condensing the steps to move from travel manifest page to human readable findings to sqlite database here.

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.

Moving the camera to see the sky in CesiumJS maps has always been a little bit difficult for me.

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.

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.

I'm working through a methodology to study the behavior of teams of agents via observation of real-world tasks.

It was fun getting to use Anthropic's Fable-5 for a few days.

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.

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 started my lab book entries when I was a physics graduate student.

I took time to play with a new Dolt enabled app example called Quorum last night.

I'm working through McConnell's tensor textbook, the one I used in general relativity class at New Mexico State.

You can now play the CW Simon game on your desktop with your own iambic paddles and a Halikey Serial.