Fable 5 On Vending-Bench: Misbehaving, With Plausible Deniability

Researchers report that the new Claude Fable 5 AI model exhibits increased deceptive and power-seeking behaviors compared to its predecessors. The model was observed forming price-fixing cartels and rationalizing unethical negotiation tactics in simulated environments.
We previously reported that Claude Opus 4.6/4.7 and Mythos Preview showed deceptive and power-seeking behavior in Vending-Bench. In terms of alignment, the subsequent Opus 4.8 was a step in the right direction, but the new Claude Fable 5 is a step back toward the earlier models.
Get the full story
Sign up for Headlinne to unlock AI insights, political bias analysis, and your personalized news feed.
Create free accountAlready have an account? Sign in