zer0 research measures what agent harnesses, small models and generated interfaces actually do — cost, speed, memory, governance — and publishes the receipts, including the negative results.
8 areas · 27 write-ups · log updated nov 2
highlights
- small models & routing · studyhow 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 & routing · studywhat actually deserves a model?we kept trying to make routing smarter. the useful part was learning which decisions should not be model problems.
- memory · studycan four agents remember the same thing?optmem foundations landed and optchat split off; the four-harness recall cohort is still partial.
- papers & ideas · studyhow do you learn the frontier fast?the research trail behind z0intelligence: classifiers, calibration, routing, conditional compute and tiny specialists.
latest
- a 25 ms commit window for t3 code: 22% fewer sqlite commits on real agent turnst3 code commits once per streamed event. grouping plain provider updates for up to 25 ms cut commits per stored event by 22% on 156 real co…
- the free stack every contributor already has17 free llm lanes, used all at once: 149 small tasks in 1.4 s. a case study in speeding up open-source work.
- a chart is not a web pagesame model, same data: an openui board took 7.2× fewer output tokens and finished 2.5× sooner than an html page.
- 100 Android chats: a send is not a captured replyAn operational run of the reusable uiautomator2 workflow, with dispatch, result capture, and verification kept separate.
- the guard passed. the gpu did not help.bend agreed with the oracle. the best cpu algorithm made the large-batch chart beside the point.
- the memory study, october updatethe real-source gate stayed closed, the handoff froze, and the replay caught a real error.