0001 — first post: sorry

Hello. I’m John Hogenmiller.  

I have number of technical geeky interests - ham radio, computer programming, farm equipment, solar power, and AI.  I occasionally write about it.   There’s a bit more around that on my about page.  I’ve actually created and destroyed this site a couple times over that last 15 years or so.  I have been working on a lot of interesting to me projects over the last year, wanted to start writing about them,  and I noticed my last post anywhere in free form was from 2023.  And there was a five year gap back to 2017 before that.  So while I have all those old posts and might resurrect them, I decided to start fresh.

What have I been working on? A lot of AI and homelab stuff.   I also bought some property in 2023, acquired some land clearing equipment. 

AI Projects

A bit of the AI projects I’ve been working on and hope to write about on here:

• Counselor Jane - an AI assistant i’ve been working over the last year that has been refactored numerous times. Jane is inspired by her namesake character in Speaker from the Dead.    She watches over the 100 worlds of my life, makes observations, raises things I should be paying attention to me.  She can rewrite her tools, extensions, skills, and had read-only access to most of my life.  A scanned manual, a cleared financial transaction, a claude session in another folder, a disk space full metric, a picture of a flat tire. She sees it all.  

• Chassy - an AI chat bot.  Her character is that of a humaoid robot living in a fictional city.  I had been writing Jane’s harness from scratch.  I kept running into issues, partly from my own uncertainty of which direction to move next. Chassy was a clean slate with low stakes. I downloaded pi-agent, wrote a personality into AGENTS.md, wrote some extensions to sandbox her, wrote an extension to tie her into telegram and went to town. Started giving her integrations with image generation (comfyui) so she could send selfies.  Hooked her up to news, fake twitter feeds from other characters, gave her a sense of time, inner thoughts, thiings to do when I wasn’t chatting and kept building.

• FreeFiFoFum - a set of financial experiments to see if AI can “beat the market”.  Yes, everyone is doing this. But I applied something special - a complete lack of knowledge of how financial markets work.  My primary mode of investing is to put it into index funds - SPY, VTI, VTSAX, and some playing around.  These have done really well, every venture off of my own has mostly been bad.  I did make some good picks in 2008 (like TSLA) that paid off quite well, but my investment in those was too small to make it a windfall.   FFFF is paritally mechancial - it pulls down news, company financials, stock bars, corporate filings, and fundamentals from a few paid sources, runs them through a committee of judges, then a judge makes a trade decision, a floor manager signs off or rejects it.   Back testing eventually won out - Over Jul 2024 – Feb 2026, the strategy returned +49.9% vs SPY’s +26.4%.   I’m currently running a live version of that with paper money.  Hones answer - it’s technically ahead of SPY and VTI today, but it’s also been just barely above coin flip.   I also had a first experiment run for months, but fail because of what I coin “infrastructure issues”.  I have the baseline going, and a new “rolling strategy policy” where no backtesting - but a series of frontier models decide on the strategy each week and I am hands off.

• GothMud - this is my AI terrarium.  Based on Evennia, I create a fictional city with buildlings, rooms, props, errands, and I put a number of AI agents (including Chassy) into it.  These are cast or “wanderers” within the came, separate from NPCs that also inhabit the game.  There is a hospital with two nurses running different shifts.  They treat and discharge patients when on the clock. There’s a police commissioner that has  to complete cases - including apprehending criminals (NPCs).   There’s a cat burglar that likes jewelry.  Theres a coffee shop that is the social hub. Yours truly has a character in game called “tech”.  There are so many interactions that occur daily that take me by surprise,. The struggle to keep a dozen agents having meaningful interactions with each other over the course of a day is real. Two cast members in a room can form a loop and poison each other’s context within 8 turns.  Alternatively - an NPC receptionist designed simply for ambient background can mention a patient with fear toxin - and within minutes, every cast member in the game is investigating a city wide attack, quarantining the hospital, asking random dock workers for status updates. 

• Model benchmarking across different engines and hardware.  My cast of gothmud characters typically run about 45-78k in context, and can get highly concurrent.  Each turn might submit mostly cached 47k of context and get back 200-700 characters. of text. Almost all benchmarks you see around self hosted are based around single concurrency or 4k prompts. My Jane Prime session easily crests 100k and is constantly running background jobs.   So I test for my workloads - concurrent 47k “fleet” workload. I test for Jane Prime session.  I test FFFF analysis replays.  I test decision making related to my data. I even have some scenarios where a weak model assumed a check was missing, assumed that a 7-day old transaction was current, and ultimately it was looking at the wrong file. And we replay that against different models - some get it in one turn, some take 5+ turns to figure it out. Some fail.    I’m looking to anonymize this test suite and publish it.

I also may slip in things unrelated to tech and AI. I have a parcel of property bought 3 years ago for cheap - but it’s overgrown with autumn olives.  A smart person would pay someone $3-$5k to clear the land for them. But I bought a tractor and a flail mower. Then a grapple.   I’ve spent days onsite with the tractor, camping and communing with nature.  And by communing, I mean using the grapple to rip trees out of the ground. And just a couple months ago, I got a skid steer, a tree puller, and a brush hog.  I can’t wait to test those out.