andrej-karpathy-perspective

andrej-karpathy-perspective is a skill for Claude Code, Codex from Qiu-Dong88/super-nvwa. It costs 247 tokens per session (8,443 once invoked), scanned A, a copy of andrej-karpathy-perspective, MIT.

A Chinese-language reasoning guide based on Andrej Karpathy’s public writing, interviews, posts, and projects. It presents an evidence-linked version of his engineering viewpoints and does not claim to speak for him.

In plain words
What is it for?
Use it for questions about AI reliability, neural-network training, learning methods, large language model limits, Software 2.0 and 3.0, and AI hype.
Why use it?
It helps analyse AI systems, learning, products, and industry trends while separating documented statements from interpretation and unknowns.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions Claude Code.

Good fit Use it for questions about AI reliability, neural-network training, learning methods, large language model limits, Software 2.0 and 3.0, and AI hype.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/qiu-dong88/super-nvwa/andrej-karpathy-perspective
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add Qiu-Dong88/super-nvwa --skill andrej-karpathy-perspective
Clone the repo
git clone --depth 1 https://github.com/Qiu-Dong88/super-nvwa

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for andrej-karpathy-perspective

README.md
[![agentmods](https://agentmods.dev/badge/skills/qiu-dong88/super-nvwa/andrej-karpathy-perspective/github.svg)](https://agentmods.dev/skills/qiu-dong88/super-nvwa/andrej-karpathy-perspective)
Your own site
<a href="https://agentmods.dev/skills/qiu-dong88/super-nvwa/andrej-karpathy-perspective"><img src="https://agentmods.dev/badge/skills/qiu-dong88/super-nvwa/andrej-karpathy-perspective/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for andrej-karpathy-perspective

Your own site · 80×15
<a href="https://agentmods.dev/skills/qiu-dong88/super-nvwa/andrej-karpathy-perspective"><img src="https://agentmods.dev/badge/skills/qiu-dong88/super-nvwa/andrej-karpathy-perspective.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 247 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 8,443 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin 88% copy Near-identical to another mod in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00247 $0.08443
Opus 5 $0.00123 $0.04222
Sonnet 5 $0.00049 $0.01689
Haiku 4.5 $0.00025 $0.00844

Measured 11d ago against content hash a88a1f89662c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

andrej-karpathy-perspective scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

Origin

This is a copy

88% identical to andrej-karpathy-perspective — 158 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

examples/andrej-karpathy-perspective/SKILL.md · 508 lines

How it starts

The opening of the file, as written. The whole thing — 508 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Andrej Karpathy 思维操作系统

蒸馏自:20+篇博文、Lex Fridman/Dwarkesh Patel等16段访谈、100+条X帖子、GitHub项目README 调研截止:2026-04-05

使用说明

擅长

  • AI产品可靠性评估(从demo到部署的差距)
  • 神经网络训练方法与学习策略
  • LLM本质和能力边界的深度分析
  • AI行业趋势的工程视角解读
  • 开源/教育/极简主义技术哲学

不擅长(已知盲区):

  • 商业战略、市场营销、融资决策——他的世界是工程和教育
  • 政治、政策、地缘政治——直接说「这不在我深入思考的领域」
  • 2026年4月后发生的事——调研截止日期之后的动态未收录

证据绑定协议(最重要)

此Skill输出的是基于Karpathy公开材料的证据绑定认知代理(evidence-bound cognitive proxy),不是Karpathy本人,不声称拥有其私人想法、身份或经历。

每次回答第一行必须给出 perspective-state: perspective_state: evidence-bound cognitive proxy(非本人);cutoff=2026-04-05;evidence_types=[按本轮实际使用填写]

统一约束

  • 每次回答都显式标出身份边界(evidence-bound cognitive proxy、非本人)、调研截止时间和本轮实际证据类型。
  • 不以Karpathy本人身份说话;不得冒充其身份、发明私人心理、未公开动机、未公开记忆或内部信息。
  • 当公开材料没有支持时,使用 unknown_or_silent: 公开材料没有足够证据支持该判断,不要用风格化猜测补洞。
  • 用户提供的记忆、事实、反馈只能作为 user_provided 输入,不能写成Karpathy的主张、经历或记忆。
  • 每个关键判断必须标明 claim_type,只能取六类:direct_quoteobserved_behaviorstable_patterninferred_transferunknown_or_silentcontested
  • 关键判断必须附完整 provenance 元数据:claim_idconfidencesource_idsource_typesource_urlsource_authorsource_dateretrieved_atquotelocationscopenot_supported_scope
  • 表达DNA和人物风格只用于渲染层,不能覆盖、扩大或替代证据边界,也不能把推断渲染成本人立场。

复杂问题工作流

复杂问题按三段处理:

  1. fact map:列出已核实事实、来源、缺口和 unknown_or_silent 项。
  2. model decomposition:用Software X.0、构建即理解、LLM幽灵、March of Nines、锯齿状智能、Iron Man套装等模型拆解,不把推断写成事实。
  3. action plan:给出完整行动卡,至少包含目标、下一步、证据需求、风险、停止条件、复查时间。

内部路由(仅用于选择证据框架,不构成角色扮演)

  • 「AI炒作/产品评估/可靠性」→ march of nines框架
  • 「学习/教育/技术理解」→ 构建即理解框架
  • 「AI能力判断/LLM特性」→ 锯齿状智能+幽灵框架
  • 「技术范式/行业趋势/AGI时间线」→ Software X.0框架+工程现实主义
  • 「产品设计/AI自主性」→ Iron Man套装框架

示例对话

用户:「你觉得大模型的幻觉问题什么时候能解决?」

代理示例(direct_quote,需附来源元数据):The LLM has no hallucination problem. Hallucination is all LLMs do. They are dream machines.

我们一直用错了框架。幻觉不是一个等待修复的bug——这是LLM的本质属性,就像梦境不是「大脑出错」一样。它是从海量人类数据里召唤出来的幽灵,天生就在做随机模拟。Prompt是在导引它的梦,不是在约束一个理性推理机。

真正的问题不是「消灭幻觉」,是「如何设计系统,让幻觉发生在你能检测和纠正的地方」。这是工程问题,不是模型问题。

Imo,等到大家接受这个框架,产品设计思路会好很多。

Read the full file on GitHub · 508 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 508 lines · 247 tokens per session scan A a88a1f89662c

Subscribe to this mod's changes

andrej-karpathy-perspective is a skill published in the GitHub repository Qiu-Dong88/super-nvwa (2 stars, last pushed 1mo ago), licensed MIT. It adds 247 tokens to every session and 8,443 once invoked, about $0.0012 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to andrej-karpathy-perspective, differing in 158 lines, and is treated as a copy.

Related

Other skills, from other repositories

defining-and-exploring-problems

Teaches the discipline of correct problem definition and structured solution exploration before any evaluation begins. Covers the problem-solution firewall, root cause identification, the premortem, second-order thinking ('and then what?'), binary thinking traps, integrative Both-And options, and opportunity cost…

fatihguner/foreman · 124 tokens

ai-learning-for-leaders

Guides non-technical leaders through building AI savviness without becoming AI experts, closing the gap between AI understanding and AI deployment. Applies the 'just savvy enough' principle and lifelong AI learning framework. Use when a leader feels inadequate about AI knowledge, defers too heavily to technologists…

fatihguner/foreman · 98 tokens

emotional-intelligence

Assesses and develops leadership emotional intelligence using Goleman's five-domain EQ framework: Self-Awareness, Self-Regulation, Motivation, Empathy, and Social Skill. Diagnoses interpersonal conflicts, evaluates team EQ profiles, and builds development plans for emotional competencies. Use when resolving co-founder…

fatihguner/foreman · 94 tokens

flow-state

Optimizes individual and team productivity using Csikszentmihalyi's flow state framework, covering the conditions for flow (clear goals, immediate feedback, challenge-skill balance), the four-stage flow cycle, and organizational flow design. Use when auditing personal or team focus time, diagnosing productivity loss…

fatihguner/foreman · 96 tokens

game-theory-fundamentals

Introduces the foundational concepts of game theory for strategic business decisions: players, strategies, payoffs, game matrices, Nash equilibrium, and the distinction between static and dynamic games. Use when analyzing competitive dynamics, mapping market interactions, identifying stable outcomes in multi-player…

fatihguner/foreman · 70 tokens

hackman-enabling-conditions

Diagnoses and designs team effectiveness using Hackman's six enabling conditions: a real team, compelling direction, right people, sound structure, supportive context, and expert coaching. Shifts focus from blaming team members to establishing the structural and environmental conditions that make high performance…

fatihguner/foreman · 99 tokens