studies
the long-form, bespoke write-ups. each one has a story mode and the receipts behind it.
- small models & routinghow much of the llm do we actually need?phase 1b: which local model routes best, and why the compiler turned out to be the intelligence.
- small models & routingwhat actually deserves a model?we kept trying to make routing smarter. the useful part was learning which decisions should not be model problems.
- papers & ideashow do you learn the frontier fast?the research trail behind z0intelligence: classifiers, calibration, routing, conditional compute and tiny specialists.
- memorycan four agents remember the same thing?optmem foundations landed and optchat split off; the four-harness recall cohort is still partial.superseded by the october update →
- memorydoes optchat stay small after fifty tool calls?the transcript kept growing and the derived view stayed smaller. context bytes only, no answer-quality claim.