Home /Modules/advantage/README.md

README.md

advantage/artificial-intelligence/README.md · 40 line(s) · markdown

advantage / artificial-intelligence — courseware track

A short courseware track that reads SLeeLa's AI code through the advantage model: which approach should I draw on, and what must I check before I do?

It follows the house style of the tutorial series (standalone lessons, prev/next headers) and points at the real code in /artificial-intelligence. Nothing here claims a measured result; numbers in exercises are illustrative.

The track

#LessonYou will learn
01Evidence before trustTreat a model score as evidence: reward vs baseline, confidence n/(n+prior), "unknown is not zero"
02Assumptions of a modelRecord held/doubted assumptions for neural nets, character recognition and LLMs
03Counsel: choosing an AI approachRank approaches with mean × confidence × trust and read the cautions
04The high speed traderA runnable model: 5,000+ evals/s, about 2,000 trades/min (advanced-medium)
05Pragmatics and evolutionThe 24 pragmatics in three phases; online weight learning (advanced)
06Fail closed, and the brilliantSafe halting, refusal over clamping, and the insight channel (advanced)
07The Moral Evaluator41 yes/no points, cardinal vetoes, merit and risk (advanced)
08Tall ScienceThe United States as a cataloged Item; nouns and names read respectively (advanced)
09The medium and the bridgeA user program loads the medium, then AI modules; messages flow both ways (advanced)

AI modules are Advantage™ components under lib/advantage/modules; a user program is in user-program.

Prerequisites

Honest limits