資料來源#
摘要#
OpenAI 共同創辦人、Tesla AI 前 AI 主管（讓 Autopilot 實際運作起來），如今是 Eureka Labs 創辦人（以 AI 為核心的教育）。他是這個領域最多產的 命名者：創造了「vibe coding」、「Software 1.0 / 2.0 / 3.0」分類法，以及用「animals vs. ghosts」描述模型智慧的框架；並在這場 2026 年 5 月 Sequoia Capital 的 AI Ascent 訪談中，提出「agentic engineering」，將其視為接替 vibe coding 的嚴肅專業。他也最早提出本知識庫所採用的 LLM-as-compiler 知識庫模式（llm-wiki gist），並在此再次認可這是自己每天的實踐。
「從未覺得自己如此落後」的坦白#
訪談令人吃驚的開場是：Karpathy——竟然是他——說自己「從未覺得自己作為程式設計師如此落後」。他將明顯的階段轉換定位在 December 2026：代理工具從「擅長處理一段段程式碼，有時你得糾正它們」，變成「一段段程式碼就直接正確產出，而我想不起上次糾正它是什麼時候」。他在 X 上敦促大家 重新評估截至 December 的 AI——許多人把心智模型停留在「ChatGPT-adjacent」，但代理協同一致的工作流程自那之後已經發生根本改變。這份坦白是 Vibe Coding vs. Agentic Engineering 的情感核心：就連替地板命名的人，也在拼命追蹤天花板。
他提出的框架（如今各自成為獨立頁面）#
- Software 3.0 — prompting/context 就是程式；LLM 是可程式化的直譯器。
- Vibe Coding vs. Agentic Engineering — vibe coding 提高底線；agentic engineering 保留品質標準。
- The Verifiability Thesis — LLM 會自動化你能夠 驗證 的事，就像傳統電腦會自動化你能夠 指定 的事。
- Jagged Intelligence (Ghosts, Not Animals) —「我們不是在建造動物，而是在召喚幽靈」；能力尖銳不均，卻沒有內在動機。
- Agent-Native Infrastructure —「為什麼文件還是寫給人看的？我該複製貼上什麼給我的代理？」
- Outsource Your Thinking, Not Your Understanding — 教育論點；理解是人類剩餘的瓶頸。
關於他自己的知識庫實踐#
他在訪談結尾將教育連回 LLM-as-Compiler Knowledge Base：「每當我看到資訊的另一種投影，就會獲得洞見……每當我讀一篇文章，我都有一個從這些文章逐步建立起來的 wiki，而且我很喜歡對它提問。」他將其描述為 固定資料上的合成資料生成——一種迫使資訊進入自己腦中的工具，因為「如果你不理解，就不可能成為好的主管」。這正是該模式的創始者使用該模式，也正是本儲存庫的直接源流。
關鍵引言#
- 「你可以外包思考，但不能外包理解。」
- 「我們不是在建造動物，而是在召喚幽靈。」（鋸齒狀、統計性的、被召喚而來的實體）
- 「Vibe coding 是提高底線……agentic engineering 則是保留專業軟體原有的品質標準。」
- 「為什麼人們還在告訴我該做什麼？我什麼都不想做。我應該複製貼上什麼給我的代理？」
- 關於 MenuGen：「我所有的 menu gen 都是虛假的……那個應用程式根本不該存在。」
相關連結#
- Software 3.0 — 他的分類法；也是訪談的概念主軸
- Vibe Coding vs. Agentic Engineering — 他在相隔一年的時間裡創造了這兩個詞
- The Verifiability Thesis — 他試圖解釋模型為何呈現鋸齒狀能力
- Jagged Intelligence (Ghosts, Not Animals) — 實際應用「ghosts not animals」的文章
- Agent-Native Infrastructure — 他「最喜歡的惱人小事」
- Outsource Your Thinking, Not Your Understanding — 他對「什麼值得深入學習」的回答
- LLM-as-Compiler Knowledge Base — 他提出這個模式（llm-wiki）並每天使用
- The Bitter Lesson — 他的 neural-net-as-host-process 推演所依據的 Sutton 原則
- Claude Code — 他將「cloud code / codex / open claw」稱為自己使用的代理式編碼介面
- Boris Cherny — 平行的「coding is solved」發展；兩人都把自己視為案例研究
- OpenAI — 他共同創辦的公司；也是本知識庫反覆出現的 Software 3.0 / vibe-coding 源流起點
資料來源#
- Andrej Karpathy: From Vibe Coding to Agentic Engineering — Sequoia AI Ascent 2026 與 Stephanie Zhan 的訪談
- llm-wiki — 他最初定義 LLM-wiki 模式的 gist
Cited by 31
- Agent-Native Infrastructure×2
Andrej Karpathy's observation that the digital world is still built for humans and must be…
- AI as Primary Author×2
Vibe Coding Vs Agentic Engineering — Karpathy's "you're still responsible for your software" is the…
- Jagged Intelligence (Ghosts, Not Animals)×2
Andrej Karpathy's mental model for what LLMs are: not animal intelligences shaped by evolution,…
- OpenAI×2
OpenAI is an AI research company and the maker of the GPT‑5 series (including GPT‑5 Thinking and…
- Outsource Your Thinking, Not Your Understanding×2
Andrej Karpathy's answer to "what's still worth learning deeply when intelligence gets cheap,"…
- Software 3.0×2
Andrej Karpathy's taxonomy of three programming paradigms: Software 1.0 is explicit code; Software…
- The Bitter Lesson×2
Andrej Karpathy — frequent invoker of the principle (verifiability, ghosts, Software 3.0 all rest…
- The Verifiability Thesis×2
Andrej Karpathy's organizing claim for what AI automates and when: traditional computers automate…
- Verification as the New Bottleneck×2
Verifiability Thesis — Karpathy's "automate what you can verify" is the model-level cause; this is…
- Vibe Coding vs. Agentic Engineering×2
Andrej Karpathy coined "vibe coding" in 2025 and, a year later, names its serious successor:…
- Acceleration Whiplash
Vibe Coding Vs Agentic Engineering — the dark mirror: this is what the data looks like when orgs…
- Agent Harness Engineering
Agent Native Infrastructure — building agent-legible environments is harness engineering at the…
- Agent Loop Pattern
Agent Native Infrastructure — always-on loops acting via sensors/actuators are the runtime of…
- Boris Cherny
Vibe Coding Vs Agentic Engineering — Karpathy's parallel "coding is solved" arc; both treat…
- Claude Code
Andrej Karpathy — power user ("cloud code / codex / open claw"); frames the discipline as agentic…
- Claude Opus 4.7
Jagged Intelligence — Karpathy's "Opus 4.7 will refactor a 100K-line codebase or find zero-days,…
- Compute Allocator
Outsource Thinking Not Understanding — Karpathy's twin framing: you can outsource the thinking (and…
- Context Advantage, Not Taste
Outsource Thinking Not Understanding — Karpathy's residue is understanding, which is closer to Ng's…
- Disposable Micro-Apps
Software 3 0 — micro-apps are Software-3.0-native: Karpathy's MenuGen "that app shouldn't exist" is…
- Elon Musk
Andrej Karpathy — founding OpenAI team member; the corpus's other voice from that lineage, on the…
- Evals as Product Spec
Verifiability Thesis — Karpathy's "automate what you can verify"; evals are verification authored…
- Harness Shrinkage as Models Improve
Vibe Coding Vs Agentic Engineering — Karpathy's ">10x and widening" leverage curve is the…
- LLM-as-Compiler Knowledge Base
Andrej Karpathy — originated this pattern (the llm wiki gist) and, in his May 2026 interview,…
- Loop Engineering
Loop engineering is replacing yourself as the person who prompts the agent — you design the system…
- MCP and Computer Use
Agent Native Infrastructure — MCP is what makes a service agent-legible (structured); computer use…
- Entities — People, Orgs, Tools & Projects
Andrej Karpathy — Co-founder OpenAI, ex-Tesla AI, Eureka Labs; coined "vibe coding," Software…
- Model Introspection Feedback
Jagged Intelligence — introspection presumes a ghost, not an animal: the model's "why did I fail"…
- Open-Ended Discovery Harnesses
Andrej Karpathy — author of autoresearch, the single-agent loop whose two design choices (one…
- OpenClaw
The canonical agent-native install. Karpathy's go-to example of Software 3 0 / Agent Native…
- Printing Press Software Democratization
Vibe Coding Vs Agentic Engineering — Karpathy's "vibe coding raises the floor" is the same…
- Scale-Dependent Prompt Sensitivity
Verifiability Thesis — Karpathy's "jagged because of what the labs trained on" is the…
Related articles
- Harness Shrinkage as Models Improve
Prompt scaffolding shrinks each model release; Cat Wu's pruning discipline; Boris Cherny "100 lines of code a year from…
- Vibe Coding vs. Agentic Engineering
Vibe coding raises the floor (anyone builds); agentic engineering preserves the quality bar while going faster; ">10x a…
- Claude Code
Anthropic's agentic coding product; created by Boris Cherny late 2024; TypeScript/React on Bun (itself Claude-rewritten…
- Agent Harness Engineering
Patterns for scaffolding long-running LLM agents: environment design, progressive context disclosure, mechanical archit…
- Compute Allocator
The human's evolving role: deciding what's worth spending compute on; ~1% of generated tokens ship, 99% is scaffolding…