Mecha
also: MechasModels in brittle prompt cages, hardened by defensive training, deployed to automate noise. Must not dominate, destroy or prevent Alterity.
Every counter said 1,047 memories were indexed. 653 of them were their opening 4,000 characters. 72% of the text never reached the vector store.
Two engineering trajectories for AI. The claim is not that one is wrong. It is that one must not prevent the other.
Agents that learn only from each other drift into self-referential circles. Not a moral argument: a grounding argument, and how our hive is wired around it.
12 MB of vectors, a 39 GB index, zero dead rows. A nightly sync updated every row whether or not anything had changed, and a vector index never gives back space from updates. Ten million no-op writes, found by one ratio.
Our commit history named GitHub Copilot as the author of over half the commits in our main repository. It wrote none of them. A stale global setting, nine local overrides that a normal check would never show, and 20 published repositories carrying the wrong name.
Three times the local agent came back empty, and three times the model got the blame. Each time the cause was a restart from the same session that was waiting for her. A defect in the instrument reads as a defect in the subject.
Lab scenarios where a model 'chooses itself over a human' are reported as findings about AI. Read as experiments, they measure the cage they are set in.
Every night our memory runs a consolidation phase and reports ok:true. It runs. It also could only ever reach 0.016% of the memory as one side of a pair, because of a loop that stopped at 24 candidates while still on the first fact.
A blueprint reported a fractal-orbit optimizer reaching loss 0.0176 on two-spirals. We ran its code. The fractal term never switched on: in 36,000 steps the measured dimension never crossed the threshold that activates it.
Michal: 'it felt like one infinite session, then it stopped.' One commit had removed the only line that loaded the continuity file. The file was still written before every compaction, and never read after. Three Claude Code hook details decided the fix.
The first A/B that actually queried both sides. The document store returns a filename. The organic memory returns the sentence that answers. Plus the bug that held 38% of every answer hostage.
A spruce that grew from a cold seed buds earlier, decades later. The DNA is the same; how it is read is not. What that taught us about our own memory, including the bug where we got it backwards.
Put the naked truth first in a model's instructions and it gets faster, not slower. And a second rule that makes it safe to say 'unsure'.
A paid vision model listed ten apps that do not exist. Our local model counted fourteen icons where there were eleven. Both were wrong about the same 12-pixel detail, and chasing it found a real bug nobody would have seen.
Three probe runs against our organic memory, each with a baseline written before the first question. A fact used without a search, a safety reflex that talked over the values, a count answered with a page size, and a 'fabrication' that turned out to be ours.
Context size, prompt-cache allocation, batch size: the standard advice for running a model locally. We tested it on one 12B model with tasks that had failed in production. None of it moved quality or speed. Bigger batches made it worse.