Mythos and Fable are the same llm. Fable has an extra tool that's in front of it that decides to accept the promp or not.
And Sonnet has a similar classifier in front according to the article:
> it’s the first Sonnet model to launch with cyber safeguards
Hence why it is no longer dangerous, yes
alt Hacker News
And Sonnet has a similar classifier in front according to the article:
> it’s the first Sonnet model to launch with cyber safeguards