Artificial Fallibility Labs
We build research instruments on one premise: error is structural, not accidental. So our tools interrogate their own output — and show you what survives.
the model suggests · the human decides
↓The model reads your paper, argues its findings, and cites the exact passage each one rests on. References are checked against live sources — never from memory. A counter-pass then tries to refute every finding. You decide what enters the review.
Try it — no account needed →An editor where your document is verified while you type. You name your tables, figures and claims — so failures arrive in your words, before you ever see the PDF, and a coauthor's changes are accepted or rejected in place. Everything except the PDF runs in your browser.
EXACTTEX — our document language with
LaTeX as its backend, created at AF Labs. Rename your
.tex to .xtex and it keeps working, byte for
byte.
open source · MIT repository opens this week
Every claim is interrogated before it ships.
What survives interrogation is worth keeping.
These tools are the working method of the Philosophy of Artificial Fallibility — a research programme on error as a structural property of computational artefacts — turned into software.
Read the philosophy →