Simon Willison added support for Anthropic's newly released Fable 5.2 and Mythos 5.2 models to his llm-anthropic tool. He tested image generation across all reasoning levels and discovered a new bug in Fable 5.2's max effort mode that runs out of tokens without producing output.
Background
llm is a command-line toolkit by Simon Willison for interacting with various LLM providers. Anthropic recently released its Fable and Mythos model series with multiple reasoning tiers.
- Source
- Simon Willison
- Published
- Nov 10, 2026 at 07:58 AM
- Score
- 5.0 / 10