Topic tag
model behavior
3 guides in the catalogue cover this topic.
- Nº 013 The new Claude lineup and what it breaks Foundations · Broad
Claude's July 2026 lineup is four models: Fable 5, Glasswing-gated Mythos 5, Sonnet 5 at intro pricing, and Opus 4.8, plus the three migration changes that bite.
- Nº 021 Judge whether AI has original ideas Foundations · Broad
Whether AI can have original ideas is a debate that keeps moving the goalposts. A way to judge it honestly: read the trend line, and see why learning to predict text can build real understanding.
- Nº 031 Why AI makes slop and how to catch it Practice · Broad
Models got good where the work grades itself, and they aim at the most likely answer, which in design and writing is the average one. The fix: break your quality standard into checkable rules and keep human judgment for taste.