Built, released, and defended orally. This lesson sits inside Module I — Building new benchmarks — of Evaluation Benchmarks, the course that anchors the Advanced AI Research program. It is not a survey; it is the specific, working understanding of "Capstone: An original benchmark" that the rest of the course assumes you carry forward.
- 01Define Capstone: An original benchmark in the precise sense used across Evaluation Benchmarks.
- 02Recognize when Capstone: An original benchmark is the correct lens for the situation in front of you, and when it is not.
- 03Apply Capstone: An original benchmark to a concrete case drawn from Building new benchmarks, and defend the result in plain language.
- 04Connect Capstone: An original benchmark to the adjacent lessons in this module without collapsing the distinctions between them.
The idea, stated plainly
Built, released, and defended orally. That single sentence is the whole lesson in compressed form. The rest of the reading unfolds it — what it means when the terms are taken seriously, where it comes from, and what work it does inside Evaluation Benchmarks. Read the sentence, then read it again after the sections below; it should carry more weight the second time.
Why it belongs in Building new benchmarks
Module I exists because the applied piece. "Capstone: An original benchmark" is one of the pillars of that module: without it, the later lessons either become memorization or lose their bite. Notice which earlier lessons this one leans on, and which later lessons will lean on it — the shape of the module is easier to see once you place this piece.
How the School of Artificial Intelligence faculty use it
In practice, working school of artificial intelligence professionals reach for this idea before they reach for a formula or a tool. It is a way of framing the problem so that the right question comes first. The mark of understanding is not that you can recite Capstone: An original benchmark; it is that you catch yourself using it, unprompted, when the situation calls for it.
Common misreadings
The most frequent error is to treat Capstone: An original benchmark as a slogan and skip the mechanics. The second most frequent is the opposite — treating the mechanics as the point, when the mechanics are only there to make the idea usable. Both errors collapse the same distinction, and both are correctable by returning to the one-line summary and asking what it actually claims.
- Capstone: An original benchmark is a working tool, not a slogan.
- Its meaning is set by the module it lives in: Building new benchmarks.
- Understanding is demonstrated by unprompted use in the correct situation.
- The adjacent lessons in this module are its natural context; read them together.
Compose the terminal work for Module I of Evaluation Benchmarks. It should bind every lesson in the module into a single artifact that a working practitioner would find useful. Anchor it in Capstone: An original benchmark and let the other lessons play their supporting roles.
Deliverables
- — A written thesis, no fewer than 3,000 words, arguing a defensible position.
- — A short accompanying presentation suitable for an oral defense.
- — A practical artifact — worksheet, checklist, model, or brief — that a peer could use.
- — A short reflection describing what the work taught you that the lessons alone did not.
Rubric
- — Coherence — the pieces reinforce a single argument.
- — Rigor — claims are supported, sources are named, limitations are declared.
- — Usefulness — a colleague could pick up the artifact and act on it.
- — Voice — the writing has an author; the artifact has a point of view.
- — Durability — the work would remain intelligible five years from now.
Oral Defense
- — Restate the thesis in one sentence.
- — Name the strongest counter-argument and address it directly.
- — Point to the single most surprising thing you learned.
- — Identify what you would change if you were doing the capstone again.
- 513 — Evaluation Benchmarks, Module I: Building new benchmarks — The parent module for this lesson. Re-read the module blurb after finishing the lesson.
- The Anabasis Academy — School of Artificial Intelligence, Advanced AI Research — The wider program this lesson serves; the Certificate in Advanced AI Research (Expert tier). Admission requires the AI Foundations and AI Engineering certificates or the equivalent in industry. credential ultimately certifies mastery of ideas like this one.