Home /Modules/advantage/03-counsel-choosing-an-approach.md

03-counsel-choosing-an-approach.md

advantage/artificial-intelligence/03-counsel-choosing-an-approach.md · 30 line(s) · markdown

Lesson 03 — Counsel: choosing an AI approach

Series: index · prev: 02

counsel ranks sources by score = mean × confidence × trust and lists things to verify and cautions:

cd advantage
make run-counsel

Reading a ranking

A high mean with two runs and a doubted assumption can rank below a modest mean with many runs and no doubts. That is intended: the module prefers a trusted modest gain to an untested large one.

Exercise

Model A: mean 0.4, 3 runs, trust 1.0. Model B: mean 0.5, 12 runs, trust 0.5. Which ranks higher? Answer: A = 0.4×0.5×1.0 = 0.20; B = 0.5×0.8×0.5 = 0.20 — a tie. Verify one assumption of B and it wins.

Next: the same discipline applies to trades; see SUPPORTED.MODELS.md.