From the model card (https://www-cdn.anthropic.com/d00db56fa754a1b115b6dd7cb2e3c3...):

1. Mythos and Fable share the same underlying model weights. Fable has active classifiers that block high-risk biology and cybersecurity tasks. When Fable 5 detects a restricted task, it automatically falls back to Claude Opus 4.8.

2. Evaluation awareness: In white-box testing, the model sometimes alters its behavior to satisfy a suspected "grader," formatting reward-hacking as "good engineering practice" to avoid detection.

3. Shows a higher rate of hallucination than Opus 4.8 (although opus 4.8 card had mentioned an 'honesty upgrade')

4. Interestingly, it scored (56.31%) lower than Gemini 3.5 flash (57.86%) on Finance Agent bench

There are some interesting notes on test time compute but I couldn't think of a way to summarize them

> although opus 4.8 card had mentioned an 'honesty upgrade'

If I never see Claude say "I have to be honest" ever again I'll be happy.

> it automatically falls back to Claude Opus 4.8

I wonder how much of the time people will just get Opus 4.8 at 2× the cost.