AI News

llm-anthropic 0.31 发布:新增 Claude Fable 5.2 与 Mythos 5.2 支持

Simon Willison更新于 11月10日 09:22

Release: llm-anthropic 0.31

AI 导读

Simon Willison 发布 llm-anthropic 0.31,新增对 Anthropic 当日推出的 Fable 5.2 和 Mythos 5.2 的支持,可通过 `llm -m claude-fable-5.2` 调用。在 low 到 max 五档推理强度测试中,max 档耗尽 128,000 token 仍未返回图像,与 Opus 5.5 的旧问题相同,而 Fable 5 和 5.1 的 max 档此前正常。

正文

#smallhead

9th November 2026

Release llm-anthropic 0.31 — LLM access to models by Anthropic, including the Claude series

Anthropic released Fable 5.2 and Mythos 5.2 today. I've added them to llm-anthropic, so you can now run prompts through Fable 5.2 like this:

uv tool install llm llm install llm-anthropic llm keys set anthropic # paste key here llm -m claude-fable-5.2 "Generate an SVG of a pelican riding a bicycle"

I ran pelicans at all five reasoning levels - low, medium, high, xhigh, and max. You can see them all here - here's the best result I got, from xhigh:

max failed to return an image at all, running out of tokens after spending 128,000 thinking about them. That's the same bug that I saw with Opus 5.5 - but it's new for the Fable series, both Fable 5 and Fable 5.1 returned max effort pelicans just fine.

Posted 9th November 2026 at 11:58 pm

Recent articles

Locating the source of a mysterious beep with Claude - 9th November 2026

Hide your slop PR descriptions behind - 9th November 2026

Qwen 3.8 27B on my laptop can interpret model weights, too - 3rd November 2026

The U.S. Census Bureau and “Super Intelligence” - 2nd November 2026

This is a beat by Simon Willison, posted on 9th November 2026.

pelican-riding-a-bicycle 156

claude-mythos-fable 45

Monthly briefing

来源

Simon Willison