AI Field Notes

6 篇文章 1 个主题模块 进入文章后，左侧会展开本课程章节

01 模型与 Agent 工程

  1. 01 AI Field Notes · AI Field Notes AI 研究档案AI research archive A quiet, bilingual reading room for technical essays on reasoning models, coding agents, and the systems around them.一个安静的双语阅读空间，整理关于推理模型、代码智能体及其系统环境的技术长文。 →
  2. 02 Controlling Reasoning Effort in LLMs · AI Field Notes It has been almost two years since OpenAI released o1, a model that popularized the idea of LLM-based reasoning models. DeepSeek-R1 followed about four months later, together with details of a reinforcement learning with →
  3. 03 GPT-5.6 Model Family and Reasoning-Effort Architecture · AI Field Notes A public-evidence deep research report on Sol, Terra, Luna, reasoning effort, Pro mode, and Ultra/multi-agent execution →
  4. 04 Skill Issue: AutoResearch and the Loopy Era of AI · AI Field Notes | Field 字段 | Value 内容 | | --- | --- | | Video ID | kwSVtQ7dziU | | Duration 时长 | 01:06:31 | | Chapters 章节 | 13 | | Bilingual semantic paragraphs 双语语义段落 | 134 | | Transcript source 字幕来源 | User-provided English auto-genera →
  5. 05 From Vibe Coding to Agentic Engineering · AI Field Notes | Field 字段 | Value 内容 | | --- | --- | | Video ID | 96jN2OCOfLs | | Duration 时长 | 00:29:45 | | Chapters 章节 | 9 | | Bilingual semantic paragraphs 双语语义段落 | 59 | | Transcript source 字幕来源 | User-provided English auto-generate →
  6. 06 Controlling Reasoning Effort in LLMs · AI Field Notes It has been almost two years since OpenAI released o1, a model that popularized the idea of LLM-based reasoning models. DeepSeek-R1 followed about four months later, together with details of a reinforcement learning with →