Understanding AI via Hand Math: CU Professor Releases Agentic AI Worksheets
ProfTomYeh · x · 2026-08-08
To prevent over-reliance on AI and the illusion of understanding, the author designed worksheets that turn complex Agentic AI concepts into simple math problems solvable by hand.
The first five problems cover fundamental mechanisms:
- Count the tokens: Split text on spaces, one word per box.
- Subword splitting: Demonstrates how one word can be three tokens.
- Punctuation counts: Marks are counted as tokens too.
- Tokens per word: The ratio that turns words into a bill.
- Context window fit: Evaluates if a document fits against a specific context window.
The author notes that while we used to practice concepts via coding, asking AI to write code has become too easy, creating a false sense of competence. Recasting concepts as manual math forces genuine comprehension.
More from Research
- AI will be superhuman at science regardless, and Europe can't opt out — teortaxesTex · 2026-10-16
- SERO augments long-horizon agentic RL with executable oracle continuations — Shanghai-AI-Laboratory · 2026-10-16
- Tsinghua and Amap propose OmniVerifier-C1, a graded verifier beating binary judges — Bowei Liu · 2026-10-16
- Alibaba open-sources MAI-Gym, an all-in-one GUI agent eval and RL training platform — Tongyi-MAI · 2026-10-16
- Peking University's SimForcing distills simulation motion priors into robot world models — PekingUniversity · 2026-10-16
- CoWorld Reasoner uses an evolving video world model as a visual reasoning engine — ModalityDance · 2026-10-16