Takajo AI Lab

Notes — Research Log

What we found in the field.

Hands-on model evaluations, prompt engineering observations, and the questions that come up when you actually run the output. Short pieces, written close to the work.

2026.07.04

Claude Fable 5 Hands-on Verification

Marketing vs. Reality — Reasoning, Self-verification, and the Stripe Case

Fable 5 is not the "best general-purpose model." Failure to evaluate source reliability, difficulty maintaining logical consistency, unused tools, defensive responses — structural weaknesses in how it conducts investigations, not just individual answers. Stripe 50M-line case study analysis. Full conversation transcript published.

Read