llm 0.32a2
LLM 0.32a2 版本发布，重要更新包括：大多数具备推理能力的 OpenAI 模型现已从 /v1/chat/completions 端点迁移至 /v1/responses 端点，支持 GPT-5 类模型在工具调用间进行交错推理。用户现在可以通过不同颜色查看 OpenAI 模型的推理令牌摘要，也可使用 -R 或 --hide-reasoning 参数隐藏推理过程。
相关报道
Andrej Karpathy suggests prompting LLMs to output responses as HTML for richer visual formatting, and argues that while audio is the preferred input, vision (images, animations, video) will become the dominant AI output. He envisions a progression from raw text to interactive neural videos and simulations, highlighting the need for better input methods like pointing and gesturing.