AI Skills AI技能 3h ago Updated 1h ago 更新于 1小时前 49

Prompt, Context, Graph, Harness: The Way We Talk to LLMs Keeps Changing 提示词、上下文、图谱、驾驭:我们与LLM的交互方式不断变化

Harness engineering represents the latest evolution in how AI systems are built, reframing the model as just one component within a broader "exoskeleton" of tools, memory, state, and guardrails Sam Altman's public acknowledgment that "the harness and the model are no longer entirely separable" signals a major industry shift away from treating raw LLMs as standalone solutions The discipline evolved through four distinct phases: Prompt Engineering (2023), Context Engineering (2025), Graph Engineer Sam Altman公开承认"harness和model不再可分离",标志着AI工程范式从纯模型竞赛转向系统级工程 Harness Engineering = Agent = Model + Harness,模型仅负责推理,其余(工具、记忆、状态、权限、反馈循环)均由harness承担 AI工程演进脉络:2023 Prompt Engineering → 2025 Context Engineering → 2025-2026 Graph Engineering → 2026 Harness Engineering 当所有开发者使用相同的推理引擎时,harness成为真正的产品差异化来源 每次

68
Hot 热度
72
Quality 质量
70
Impact 影响力

Analysis 深度分析

TL;DR

  • Harness engineering represents the latest evolution in how AI systems are built, reframing the model as just one component within a broader "exoskeleton" of tools, memory, state, and guardrails
  • Sam Altman's public acknowledgment that "the harness and the model are no longer entirely separable" signals a major industry shift away from treating raw LLMs as standalone solutions
  • The discipline evolved through four distinct phases: Prompt Engineering (2023), Context Engineering (2025), Graph Engineering (2025–2026), and Harness Engineering (2026), each expanding the unit of engineering
  • Viv Trivedy's equation "Agent = Model + Harness" captures the core insight: the model handles reasoning while everything else—tools, state, evaluation loops, error recovery—constitutes the harness
  • As access to identical reasoning engines becomes commoditized, the harness itself is becoming the real differentiator and product in AI system development

Why It Matters

This article captures a pivotal conceptual shift in AI engineering that directly affects how practitioners should allocate their efforts and resources. As raw model capabilities converge across providers, the competitive advantage increasingly lies in the surrounding infrastructure—the tools, memory systems, guardrails, and feedback loops that enable models to operate reliably in production. For AI professionals, understanding this evolution is essential for making strategic decisions about system architecture, team skill development, and where to invest engineering talent.

Technical Details

  • Prompt Engineering (2023): Focused on crafting input instructions (e.g., "Let's think step by step") to steer standalone LLM outputs; the system was viewed as a "brain in a jar" with no external capabilities
  • Context Engineering (2025): Pioneered by Tobi Lütke and Andrej Karpathy; shifted focus from how to ask to what information the model receives, involving retrieval systems that populate the context window with relevant documents and prior history
  • Graph Engineering (2025–2026): Emerged with multi-agent systems using frameworks like LangChain and LangGraph; represented workflows as graphs with nodes (tasks), edges (transitions), and explicit rules for state management, routing, retries, and human intervention
  • Harness Engineering (2026): Defined by Viv Trivedy as building a pre-wired autonomous exoskeleton around the model; the harness includes tools the model can call, durable state it maintains, guardrails it operates within, and evaluation loops that catch and correct errors
  • Each evolutionary phase absorbed the previous one rather than replacing it—harness engineers still write prompts, manage context, and design workflow graphs, but the unit of engineering has expanded from a sentence to a window to a network to the entire operational apparatus

Industry Insight

  • Companies should prioritize investment in harness infrastructure—tool integrations, memory systems, error-recovery mechanisms, and evaluation loops—rather than chasing marginal model capability improvements, as the harness is becoming the primary source of competitive differentiation
  • Engineering teams should broaden their skill sets beyond prompt design to include systems architecture, state management, and workflow orchestration, as these are the competencies that define effective harness engineering
  • The commoditization of reasoning engines means that AI product strategy should focus on building proprietary harnesses tailored to specific domains and use cases, since identical models wrapped in different harnesses will produce vastly different real-world outcomes

TL;DR

  • Sam Altman公开承认"harness和model不再可分离",标志着AI工程范式从纯模型竞赛转向系统级工程
  • Harness Engineering = Agent = Model + Harness,模型仅负责推理,其余(工具、记忆、状态、权限、反馈循环)均由harness承担
  • AI工程演进脉络:2023 Prompt Engineering → 2025 Context Engineering → 2025-2026 Graph Engineering → 2026 Harness Engineering
  • 当所有开发者使用相同的推理引擎时,harness成为真正的产品差异化来源
  • 每次范式转移并非取代前者,而是将其吸收进更大的工程单元中

为什么值得看

这篇文章首次以Sam Altman的公开表态为锚点,系统梳理了AI工程范式的四年演变史,揭示了行业从"造大脑"到"造外骨骼"的认知转变。对AI从业者而言,理解harness engineering是把握当前Agent系统构建方向的关键。

技术解析

  • Harness Engineering核心公式:Agent = Model + Harness,其中Harness包含工具调用、持久化记忆、状态管理、权限控制、错误恢复机制和评估反馈循环,模型仅负责推理部分
  • Context Engineering(2025):由Tobi Lütke和Andrej Karpathy推动,核心是构建检索系统,将相关文档注入模型上下文窗口,解决模型无法访问私有数据和近期信息的问题
  • Graph Engineering(2025-2026):使用LangChain、LangGraph等框架将多Agent系统建模为图结构,节点代表任务,边代表状态转移,显式定义路由、重试、人工干预等规则
  • 工程单元演变:从单句Prompt → 上下文窗口 → 工作流图 → 整个模型运行环境,每次转移都吸收前一阶段的技术而非完全替代

行业启示

  • 产品差异化重心转移:当基础模型能力趋同,真正的竞争壁垒在于harness的设计——包括工具生态、记忆架构、错误恢复机制等系统级能力
  • Agent系统构建方法论成熟:行业已从"让模型做一切"转向"为模型构建可靠的外骨骼",这要求团队具备系统架构能力而非仅提示词工程能力
  • 技术命名周期规律:AI领域约每年重新命名一次基础工程范式,从业者需关注概念背后的实质技术演进而非术语本身

Disclaimer: The above content is generated by AI and is for reference only. 免责声明:以上内容由 AI 生成,仅供参考。

LLM 大模型 Agent Agent Deployment 部署 Research 科学研究