The formal foundations of AI reasoning.
Serre AI is an independent research lab that studies reasoning in AI systems through computational complexity, verification and large-scale empirical evaluation of language models.
Research
Three programmes, one standard of evidence.
Each pursues its own questions; all three are held to the same proof.
Platform
A research platform that keeps the evidence.
Serre is the platform we build and run our own research on. Four steps, each one checkable.
Maps a field
Gathers a field's papers through their citations and records what each claims, with the passage it comes from.
Judges a direction
Tests a direction for novelty, feasibility and fit, each judgment a separate step with its evidence on file.
Plans submissions
Places committed work at venues whose deadlines it can meet, with a fallback if a paper is rejected.
Keeps the record
Logs every decision with the evidence it rested on and who made it, so it can be checked later.
Compass
Judges a direction before you commit to it.
Novelty, feasibility and fit at real venues, each judgment tied to the passage it rests on.