We’ll be spending a lot more time trying to understand the outputs of language models. A few thoughts, tips & tricks: Writing. Something I’ve had success with: Ask your LLM to explain something in ASD-STE100, it’s a c…

Andrej Karpathy 提出,随着大模型能力提升,人类的工作重心会转向“审查和理解模型输出”,而最有效的理解方式可能不是读文字,而是让模型直接生成图表、网页和讲解视频。他还给出了一个具体技巧:用航空航天领域的受控语言标准 ASD-STE100 来约束模型写作。






![[Bug]: Stdio MCP not working](https://www.chat-gpts.plus/wp-content/uploads/2026/10/15560-b111244f-768x403.jpg)
![[Bug]: llama-index-embeddings-azure-openai 0.6.0 is still dependent on llama-index-llms-azure-openai>=0.4.0,<0.6](https://www.chat-gpts.plus/wp-content/uploads/2026/10/23325-955c0d99-768x403.jpg)
