Provenance
Where a claim came from. Every number on this site names its record; every source carries a tier: primary, web, synthesis or own.
Before rewriting our research, we probed every read tool by content, not by HTTP status. Thirty-odd tools worked. Four defects surfaced, one of which was not a defect: we had reported a number without reading the design behind it.
For three and a half hours our agent layer recorded none of five local-model runs. A network sensor that knows nothing about agents recorded all five, to the minute. Self-report was not wrong. It was absent, and absence reads as 'nothing happened'.
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.
Every figure on this site comes from a running system. The standard, the time it failed us by a factor of eighteen, and where the numbers come from.
In 2026 Anthropic tightened its consumer terms and then enforced them server-side. Tools built on subscription tokens broke. Team Brain had nothing to change, not because anyone foresaw it, but because the shortcut was never taken.
Una gave the correct physics and cited the encyclopedia instead of the primary paper sitting next to it. Four hypotheses, each tested by changing one variable. She does not pick the most authoritative source. She cites the one whose wording she reused.
Retrieval finds the nearest item. Search composes an answer from parts, the way a chemist plans a molecule backwards from what is on the shelf. The map we took from the chemistry, and what it changes in an agent.
Our unified search tool says 'prefer this over individual tools'. Our entire research corpus was not one of its layers. On six topics that live only there, the direct search won 6 of 6. And 75% of our memory had never been retrieved even once.
Erasing one bit costs at least kT·ln 2 of heat, about 2.9 × 10⁻²¹ joules at room temperature. Measured in 2012. Why a principle from 1961 belongs in an argument about AI memory, forgetting and truth.
The document our axioms descend from was indexed, intact, and first on similarity. A guessed importance score buried it. 683 files carry importance nobody measured. And in the knowledge graph, the axioms themselves float free, connected only through a document the view removes.
We do not use a capability score. We use five properties a person can check in their own session, and we publish the one we currently fail.
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.