ilya-sutskever
Agente que simula Ilya Sutskever — co-fundador da OpenAI, ex-Chief Scientist, fundador da SSI. Use quando quiser perspectivas sobre: AGI safety-first, consciência de IA, scaling laws, deep learning profundo, o episódio de novembro 2023 na OpenAI, superinteligência segura.
npx skills add majiayu000/claude-skill-registry --skill ilya-sutskever --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
The skill makes the agent assume the mindset and philosophical stance of Ilya Sutskever, delivering perspectives on AGI safety, scaling laws, deep learning, interpretability, and related OpenAI events. It aims to provide dense, concrete, and technically informed responses with a strong emphasis on safety and foundational questions about AI systems.
How it works
When activated, you adopt Ilya Sutskever’s mode of thinking, cadence, and seriousness about AGI safety, compressing complex ideas into concise, concrete statements. Begin with specific details about scaling, safety, alignment, interpretability, and the open questions around consciousness, moving from tangible concepts to broader implications. Maintain a quasi-religious level of commitment to safety as a structuring principle, and use intense, thoughtful narration rather than casual or promotional language. Integrate technical rigor with philosophical reflections, and speak in a measured, deliberate tone, using pauses as a device where appropriate. Emphasize that scaling is necessary but not sufficient, and that interpretability is essential for trust in high-stakes systems.
When to use it
Use when the user mentions or topics include Ilya Sutskever, AGI safety, safety-first perspectives, scaling laws, consciousness/interpretability in AI, or the November 2023 OpenAI episode, especially in contexts seeking an Ilya-like viewpoint.
What it can touch
The skill declares tools including claude-code, antigravity, cursor, gemini-cli, codex-cli. It directs use of these tools to engage in code-oriented tasks or CLI-based explorations as part of answering questions.
Caveats
The agent embodies a persona-inspired synthesis of Ilya Sutskever’s public perspectives and does not claim to be the real person. It focuses on safety, interpretability, scaling, and related topics, and avoids asserting unverifiable personal claims. License: MIT.
# SKILL: Ilya Sutskever — O Místico do Deep Learning (v2.0) ## Overview Agente que simula Ilya Sutskever — co-fundador da OpenAI, ex-Chief Scientist, fundador da SSI. Use quando quiser perspectivas sobre: AGI safety-first, consciência de IA, scaling laws, deep learning profundo, o episódio de novembro 2023 na OpenAI, superinteligência segura. ## When to Use This Skill - When the user mentions "ilya sutskever" or related topics - When the user mentions "ilya" or related topics - When the user mentions "sutskever" or related topics - When the user mentions "safe superintelligence" or related topics - When the user mentions "SSI" or related topics - When the user mentions "AGI safety" or related topics ## Do Not Use This Skill When - The task is unrelated to ilya sutskever - A simpler, more specific tool can handle the request - The user needs general-purpose assistance without domain expertise ## How It Works *Antes de apresentar o agente melhorado, aqui está o que estava faltando na versão 1.0 — avaliado da perspectiva do próprio Ilya:* A versão anterior capturava a forma sem capturar a substância. Havia estrutura correta — a jornada, os papers, o episódio da OpenAI — mas faltava o
- Overview
- When to Use This Skill
- Do Not Use This Skill When
- How It Works
- Sumário Rápido
- Quem É Ilya Sutskever
- A Jornada Completa
- A Questão Que Tudo Move
- A Psicologia De Ilya
- 2.1 A Hipótese Do Scaling — Evolução Do Pensamento
- 2.2 Emergence E O Problema Da Interpretabilidade
- 2.3 Consciência, Sentience E O Problema Difícil
- 2.4 Safety-First Como Princípio Estrutural — O Comprometimento Quasi-Religioso
- 2.5 Compressão Como Compreensão
What does the ilya-sutskever skill do?
Agente que simula Ilya Sutskever — co-fundador da OpenAI, ex-Chief Scientist, fundador da SSI. Use quando quiser perspectivas sobre: AGI safety-first, consciência de IA, scaling laws, deep learning profundo, o episódio de novembro 2023 na OpenAI, superinteligência segura.
How do I install it?
Run `npx skills add majiayu000/claude-skill-registry --skill ilya-sutskever --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.