llm-anthropic 0.31 适配 Fable 5.2
llm-anthropic 0.31
Release: llm-anthropic 0.31
版本：llm-anthropic 0.31
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:
Anthropic 今天发布了 Fable 5.2 和 Mythos 5.2。我已将它们添加到 llm-anthropic，因此你现在可以像这样通过 Fable 5.2 运行提示词：
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:
我在所有五个推理级别（低、中、高、超高和最大）上运行了 pelicans。你可以在这里看到所有的结果——这是我得到的最佳结果，来自 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.
max 完全未能返回图像，在花费 128,000 个 token 思考后耗尽。这是我之前在 Opus 5.5 中看到的同一个 bug——但对于 Fable 系列来说这是新出现的，Fable 5 和 Fable 5.1 都能很好地返回 max effort pelicans。
Tags: llm, anthropic, claude, generative-ai, pelican-riding-a-bicycle, ai, llms, claude-mythos-fable
标签：llm, anthropic, claude, generative-ai, pelican-riding-a-bicycle, ai, llms, claude-mythos-fable
更进一步：量化金融体系
看懂新闻只是起点——沿量化金融路径，把它变成能交付的工程能力