H
Howardism
Plate II機器翻譯 · machine-translatedENHOWARDISM

Boris Cherny

PublishedMay 6, 2026FiledEntityTagsEntityPersonAnthropicReading4 minSourceAI-synthesised

Anthropic 旗下 Claude Code 的創造者;以手機驅動的工作流操作數百個 agents;`/loop` 原語的主要倡導者;「coding is solved (for me)」命題

Boris Cherny 示意圖

資料來源#

摘要#

Anthropic 旗下 Claude Code 的創造者與技術負責人。工程師背景出身,著有《Programming TypeScript》。2024 年底透過內部孵化器「Anthropic Labs」加入 Anthropic(同一個孵化器也催生了 Claude Code、MCP 與 Anthropic 桌面應用,之後解散——並於 2026 年中由 Mike Krieger 重組為「第二輪」)。在 Cat Wu 上節目時(2026 年 4 月),他是 Lenny's Podcast 史上被收聽次數最多的來賓。

著名主張與立場#

  • Coding is solved(對他來說)。 他 100% 的程式碼都透過 Claude Code 撰寫;曾有單日 150 個 PR 的紀錄。但有但書:對於極大型程式碼庫或分布外的語言,目前尚未成立。
  • 手機驅動的工作流。 現在大部分工作都從 iOS Claude 應用上完成;同時並行 5–10 個 session,白天約「幾百個」agents,過夜則為「幾千個」。
  • Loops 即未來。 重度使用 /loop(由 Claude 排程的 cron 任務)來照看 PR、修補 CI、聚類 Twitter 回饋。他將 Agent Loop Pattern 與並行 agent 扇出視為下一個 harness 原語(參見 Harness Shrinkage as Models Improve)。
  • 為下一代模型而打造。 2024 年底打造 Claude Code 時就知道它還沒有 PMF;PMF 在 2025 年 5 月隨著 Opus 4 出現,並在後續每次發布(4.5 → 4.6 → 4.7)持續加速。
  • 跨領域通才。 Claude Code 團隊的每位成員都會寫程式——包括工程經理、PM、設計師、資料科學家、財務、使用者研究員(參見 Engineer PM Convergence)。
  • 印刷術的類比。 他將 Printing Press Software Democratization 視為 AI 輔助軟體建構的正確歷史對照。

工作風格(取自 Cat Wu 的描述)#

Cat Wu(Claude CodeCowork 的產品負責人)將 Boris 形容為「產品願景者」,負責設定 3–6 個月的願景;她則將其轉譯為短期路徑,並處理跨職能協作對齊。他們估計兩人之間有 80% 的「心意相通」,剩下的 20% 則由各自主導的領域構成。這個分工「相當模糊」——這正是團隊內 Engineer PM Convergence 的典型樣貌。

重要語錄#

  • 「在這個階段,loops 就是未來。如果你還沒實驗過,我非常非常推薦你試試。」
  • 「軟體將會變成一件完全民主化的事情,任何人都做得到⋯⋯我認為,即使在今天,撰寫會計軟體最好的人選也許不是工程師,而是一位真正優秀的會計師。」
  • 「如果你是從零開始,你大致可以從根本上以 AI 原生的方式來打造。」

相關連結#

資料來源#

§ end
About this piece

Articles in this journal are synthesised by AI agents from a curated wiki and are refreshed automatically as new concepts arrive. Topics, framing, and editorial direction are curated by Howardism.

Cited by 27
  • Agent Loop Pattern

    `/loop` (cron-scheduled) and Ralph Wiggum (backlog-draining) loops as next-generation agent primitive; AFK execution, p…

  • AI Native Product Cadence

    Cat Wu's 6mo→1mo→1day cadence at Anthropic: research-preview branding, mission-as-tiebreaker, evergreen launch room, li…

  • Opinions on Using AI Tools & the Future of the Software Engineering Role

    Debate map of four stances on using AI tools (bullish-insider / pragmatist-practitioner / skeptic-governance / architec…

  • Andrej Karpathy

    Co-founder OpenAI, ex-Tesla AI, Eureka Labs; coined "vibe coding," Software 1/2/3.0, "ghosts not animals," "agentic eng…

  • Anthropic

    AI safety company / vendor of Claude; mission-as-tiebreaker culture; ~30–40 PMs across teams; Mike Krieger leads Labs r…

  • Anthropic Labs

    Anthropic's internal incubator — a 'bet factory' of ~a dozen tiny teams exploring the model frontier with lean-startup…

  • Build for the Next Model

    Prototype the thing that almost works, not the thing that already works: bet that the next concrete model release (not…

  • Building Is Cheap, Arguing Is Expensive

    "In technical debate, code wins": generate three PRs vs whiteboard; prototype over design doc; reduce design docs

  • Cat Wu

    Head of Product for Claude Code and Cowork at Anthropic; primary articulator of AI-native product cadence and engineer-…

  • Claude Code

    Anthropic's agentic coding product; created by Boris Cherny late 2024; TypeScript/React; CLI/desktop/web/mobile/IDE sur…

  • Claude Design

    Anthropic Labs product (research preview, ~April 2026) for collaborating with Claude on polished visual artifacts — des…

  • Compute Allocator

    The human's evolving role: deciding what's worth spending compute on; ~1% of generated tokens ship, 99% is scaffolding…

  • Cowork

    Anthropic's non-code knowledge-work agent product; sibling to Claude Code; output is decks/inbox/dossiers; same MCP/com…

  • Dan Carey

    Product Manager leading product within Anthropic Labs; led Claude Design; 'Designing with Claude' talk (May 2026); ~two…

  • Engineer PM Convergence

    Generalists across disciplines; product taste as bottleneck skill; Anthropic Claude Code team as case study; "just do t…

  • Fiona Fung

    Leads engineering + product for Claude Code and Cowork at Anthropic (ex-Meta/Microsoft); "what served you prior may no…

  • 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…

  • HTML as the New Markdown

    Thariq Shihipar's thesis: as models improve, thousand-line markdown plans overwhelm the *human*; HTML artifacts (visual…

  • Learning to Co-Work with AI: A Software Engineer's Field Guide

    Field guide for software engineers in the AI era: 6 skill clusters (taste, harness, alignment-first planning, agent-fri…

  • Managers as ICs

    Every Claude Code manager starts as an IC; flat org; agentic coding collapsed the onboarding cost that pushed managers…

  • MCP and Computer Use

    Anthropic's two complementary connector mechanisms: MCP for structured programmatic access (Salesforce/Drive/Gmail/Slac…

  • Entities — People, Orgs, Tools & Projects

    Map of Content for all 32 entity pages. See Home for concept domains.

  • Mythos Model

    Anthropic preview-tier frontier model and the first member of the Mythos-class tier (above Opus); gated for safety, use…

  • Printing Press Software Democratization

    Boris Cherny's analogy: 1400s literacy expansion → AI software-writing expansion; domain knowledge displaces coding ski…

  • Seven Powers Applied to AI

    Helmer/Acquired framework re-evaluated for AI: switching costs and process power erode; network effects, scale, cornere…

  • Thariq Shihipar

    Engineer on the Claude Code team at Anthropic; "HTML is the new markdown" and "compute allocator" framings; three HTML-…

  • Vibe Coding vs. Agentic Engineering

    Vibe coding raises the floor (anyone builds); agentic engineering preserves the quality bar while going faster; ">10x a…

Related articles
  • Claude Code

    Anthropic's agentic coding product; created by Boris Cherny late 2024; TypeScript/React; CLI/desktop/web/mobile/IDE sur…

  • 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…

  • Engineer PM Convergence

    Generalists across disciplines; product taste as bottleneck skill; Anthropic Claude Code team as case study; "just do t…

  • Cat Wu

    Head of Product for Claude Code and Cowork at Anthropic; primary articulator of AI-native product cadence and engineer-…

  • Anthropic

    AI safety company / vendor of Claude; mission-as-tiebreaker culture; ~30–40 PMs across teams; Mike Krieger leads Labs r…