llm-anthropic 0.31 adds Anthropic Fable 5.2 and Mythos 5.2
Original title: llm-anthropic 0.31
Willison says max reasoning on Fable 5.2 spent 128,000 tokens thinking and returned no image, a bug he also saw on Opus 5.5.
Simon Willison released llm-anthropic 0.31 after Anthropic released Fable 5.2 and Mythos 5.2. The plugin exposes Fable 5.2 as claude-fable-5.2 in the llm CLI. He ran a pelican SVG prompt at five reasoning levels and reported that max failed to return an image after exhausting thinking tokens.
Unconfirmed: The note is cut off and does not state Mythos 5.2 model identifiers or release details beyond the plugin update.
- Reasoning levels tested were low, medium, high, xhigh, and max.
- He said the best pelican image came from the xhigh level.
- He called the empty max result new for Fable 5 and Fable 5.1.
- Vendors
- Anthropic
- Products
- llm-anthropic
- AI models
- Fable 5.2Mythos 5.2
From the original article
Release: llm-anthropic 0. 31 Anthropic released Fable 5. 2 and Mythos 5.
simonwillison.net
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.