{"slug": "llm-anthropic-0-31", "title": "llm-anthropic 0.31", "summary": "Simon Willison released llm-anthropic 0.31, adding Anthropic's newly released Fable 5.2 and Mythos 5.2 models to the LLM command-line tool. Testing the models on an SVG pelican prompt across all five reasoning levels (low, medium, high, xhigh, max), Willison found that max effort failed to return an image at all, exhausting 128,000 tokens on reasoning — the same over-thinking bug he saw with Opus 5.5, but new to the Fable series since Fable 5 and Fable 5.1 returned max-effort pelicans successfully.", "body_md": "**Release:** [llm-anthropic 0.31](https://github.com/simonw/llm-anthropic/releases/tag/0.31)\n\nAnthropic [released Fable 5.2 and Mythos 5.2](https://www.anthropic.com/claude-fable-and-mythos-5-2) today. I've added them to `llm-anthropic`, so you can now run prompts through Fable 5.2 like this:\n\n```\nuv tool install llm\nllm install llm-anthropic\nllm keys set anthropic\n# paste key here\nllm -m claude-fable-5.2 \"Generate an SVG of a pelican riding a bicycle\"\n```\n\nI ran pelicans at all five reasoning levels - `low`, `medium`, `high`, `xhigh`, and `max`. You can [see them all here](https://tools.simonwillison.net/markdown-svg-renderer?url=https%3A%2F%2Fgist.github.com%2Fsimonw%2Fbcd1a1bf38b929b0bbbae2e38b808e97) - here's the best result I got, from `xhigh`:\n\n`max` failed to return an image at all, running out of tokens after spending 128,000 [thinking about them](https://tools.simonwillison.net/markdown-svg-renderer?url=https%3A%2F%2Fgist.github.com%2Fsimonw%2Fbcd1a1bf38b929b0bbbae2e38b808e97#reasoning-2). That's the same bug that I saw with [Opus 5.5](https://simonwillison.net/2026/Sep/22/opus-and-sol-and-luna/#claude-opus-5-5-max-over-thinks-to-the-point-of-breaking) - but it's new for the Fable series, both [Fable 5](https://simonwillison.net/2026/Jun/9/claude-fable-5/#and-some-pelicans) and [Fable 5.1](https://simonwillison.net/2026/Sep/1/claude-fable-5-1/#max) returned max effort pelicans just fine.\n\nTags: [llm](https://simonwillison.net/tags/llm), [anthropic](https://simonwillison.net/tags/anthropic), [claude](https://simonwillison.net/tags/claude), [generative-ai](https://simonwillison.net/tags/generative-ai), [pelican-riding-a-bicycle](https://simonwillison.net/tags/pelican-riding-a-bicycle), [ai](https://simonwillison.net/tags/ai), [llms](https://simonwillison.net/tags/llms), [claude-mythos-fable](https://simonwillison.net/tags/claude-mythos-fable)", "url": "https://wpnews.pro/news/llm-anthropic-0-31", "canonical_source": "https://simonwillison.net/2026/Nov/9/llm-anthropic/", "published_at": "2026-11-09 23:58:46+00:00", "updated_at": "2026-11-10 00:51:54.869651+00:00", "lang": "en", "topics": ["ai-tools", "large-language-models", "generative-ai", "developer-tools"], "entities": ["Simon Willison", "Anthropic", "llm-anthropic", "Fable 5.2", "Mythos 5.2", "Opus 5.5", "LLM"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/llm-anthropic-0-31", "markdown": "https://wpnews.pro/news/llm-anthropic-0-31.md", "text": "https://wpnews.pro/news/llm-anthropic-0-31.txt", "jsonld": "https://wpnews.pro/news/llm-anthropic-0-31.jsonld"}}