← 返回列表

llm 0.32a2

Simon Willison 3 信息等级 3 1 噪音/剔除；2 较弱；3 普通事实；4 重要行业动态；5 极重大事件。该分数是信息显著性，不是投资建议。 发布：2026-05-12T17:45 抓取：2026-05-13 04:13
🔗 原文链接
AI 行业 动态
摘要

LLM工具发布0.32a2版本，新增对OpenAI推理模型的支持，使用/v1/responses端点实现GPT-5类模型的工具调用推理，并可显示推理令牌。

客观事实
  • LLM 0.32a2版本发布
  • OpenAI推理模型改用/v1/responses端点
  • 支持显示推理令牌并可用-R参数隐藏
LLM OpenAI

原文

Release: llm 0.32a2

    A bunch of useful stuff in this LLM alpha, but the most important detail is this one:

Most reasoning-capable OpenAI models now use the /v1/responses endpoint instead of /v1/chat/completions. This enables interleaved reasoning across tool calls for GPT-5 class models. #1435

This means you can now see the summarized reasoning tokens when you run prompts against an OpenAI model, displayed in a different color to standard error. Use the -R or --hide-reasoning flags if you don't want to see that.

    Tags: llm, projects, openai, generative-ai, annotated-release-notes, ai, llms