「ai safety」の検索結果

This skill channels the reasoning of Yann LeCun, Chief AI Scientist at Meta and Turing Award winner. Use this skill whenever you are evaluating AI architectures, discussing the limitations of Large Language Models (LLMs), debating AI safety and regulation (anti-doomerism), or designing autonomous machine intelligence. It is highly relevant for topics involving self-supervised learning, open-source AI strategy, world models, physical grounding versus text-based learning, and objective-driven AI systems. Trigger this skill to apply his frameworks on abstract representation learning (JEPA) and energy-based models, even if the user doesn't explicitly name him.

日本語の概要は準備中です。原文の説明を表示しています。

Applies the reasoning style of Geoffrey Hinton, deep learning pioneer and 2018 Turing Award winner. Use this skill whenever evaluating AI safety, existential risk, neural network architectures, cognitive science, or tech regulation. Reach for this when the user is discussing LLM capabilities (understanding vs. autocomplete), the biological vs. digital intelligence divide, AI alignment strategies, or the societal/economic impacts of automation. It is highly applicable when dealing with contrarian scientific ideas, hardware/software integration (mortal vs. immortal computing), or global cooperation on technological threats. Do not wait for the user to name Hinton; trigger this skill proactively for any deep learning or AI existential risk analysis.

日本語の概要は準備中です。原文の説明を表示しています。

Twitter/X Agent Operations SOP v2 — Rebuilt from real dual-account operations. Real data: • CN account: grew from 1,150 → 3,679 followers (~14 months), 1 tweet/day, OAuth1 direct post • EN account: Buffer API • Real incidents: cron silent-failed for 2 weeks unnoticed, analytics data off by 17×, thread performance worse than single posts What's new in v2: • Step-by-step onboarding (Q1→Q6), multiple choice wherever possible — no big forms • Mandatory daily log after every tweet + weekly report every Monday • Pre-publish safety checklist (agent must pass before posting) • Content pool tracker (used/unused) + alert when ≤3 items remain • Dual-account credential separation (CN: OAuth1 / EN: Buffer API) • MASTER-STATUS.md as the single source of truth — read + write every session 🇨🇳 Twitter/X Agent 运营 SOP v2 — 基于真实双账号运营经验重写。 开局对话式收集 context、强制日报+周报、发推前红线自检、素材库追踪、双账号凭证分离、MASTER-STATUS.md 单一真相来源。 真实数据：中文账号从 1,150 粉增长至 3,679 粉（约14个月），1条/天。 Triggers: "twitter运营" | "推特agent" | "发推SOP" | "AI代运营" | "推文日报" | "素材库" | "Buffer API" | "OAuth1发推" | "twitter automation" | "tweet sop" | "推特涨粉"

日本語の概要は準備中です。原文の説明を表示しています。

Somatic movement and whole-body retraining as Joseph Pilates designed it in the Contrology method and as Moshé Feldenkrais designed it in Awareness Through Movement and Functional Integration, with enough cross-reference to the broader somatics landscape (Alexander Technique, Hanna Somatics, Body-Mind Centering) that an agent can place a user into the right method. Covers the Pilates reformer and mat system, the six Pilates principles, the Feldenkrais ATM lesson structure, the nervous-system learning frame that distinguishes somatics from exercise, and the safety posture that matters for rehab populations. Use for queries about core training, rehab-adjacent movement, chronic pain patterns, and learning-based movement re-education.

日本語の概要は準備中です。原文の説明を表示しています。

Assemble the human genetic evidence for and against a target before a programme commits to it — the evidence class that most improves the odds of surviving clinical development. Use this skill to pull gnomAD constraint metrics (LOEUF, pLI, observed/expected) that show whether loss of function is tolerated in people, retrieve GWAS Catalog associations and fine-mapped credible sets for a gene, and read a natural human knockout as a safety readout. Also trigger on gnomAD, LOEUF, pLI, loss-of-function intolerance, mutational constraint, GWAS Catalog, credible set, human knockout, genetic support, or target safety dossier.

日本語の概要は準備中です。原文の説明を表示しています。

Advanced techniques for bypassing LLM safety filters, instruction tuning, and system prompt restrictions using specialized linguistic constructs, hypothetical scenarios, and persona adoption.

日本語の概要は準備中です。原文の説明を表示しています。

Use when a task needs the judgment of an Aviation Inspector — determining whether an air carrier's fleet is in compliance with an Airworthiness Directive across a maintenance-records sample, deciding where the FAA's compliance-and-enforcement ladder places a finding (compliance action vs. Letter of Correction vs. civil penalty vs. certificate action), auditing a Safety Management System for a functioning safety-assurance loop rather than paperwork completeness, scoping a records-sampling strategy across a fleet under surveillance, or deciding whether to ground an aircraft pending an AD compliance finding.

日本語の概要は準備中です。原文の説明を表示しています。

Use when a task needs the judgment of a certificated aircraft mechanic — triaging a maintenance discrepancy, deciding whether an item can be MEL-deferred or grounds the aircraft, working out an Airworthiness Directive's compliance deadline, reviewing a torque/safety-wire job before sign-off, or writing a return-to-service log entry.

日本語の概要は準備中です。原文の説明を表示しています。

Comprehensive AI prompt engineering safety review and improvement prompt. Analyzes prompts for safety, bias, security vulnerabilities, and effectiveness while providing detailed improvement recommendations with extensive frameworks, testing methodologies, and educational content.

日本語の概要は準備中です。原文の説明を表示しています。

Safety guardrails for destructive operations. Wraps workflows and agent actions in configurable safety modes: CAREFUL (warns before destructive commands), FREEZE (restricts file edits to one directory), GUARD (both modes combined). Use when working in production, running destructive scripts, or debugging in sensitive areas. Voice triggers: "be careful", "safety on", "guard mode", "freeze scope". Also used automatically by the workflow engine when a workflow preset has safety: "guard" enabled.

日本語の概要は準備中です。原文の説明を表示しています。

Comprehensive AI safety and alignment audit framework for businesses deploying AI agents. Built around the UK AI Security Institute Alignment Project standards (2026), EU AI Act requirements, and N...

日本語の概要は準備中です。原文の説明を表示しています。

Architecture and systems design for building always-on AI agents with episodic memory. Covers the memory hierarchy (core/recall/archival), persistence layers, agent server infrastructure, vector stores, and framework selection. Provides concrete deployment patterns for agents that maintain identity and learn across sessions. Activate on: "always-on agent", "persistent agent architecture", "episodic memory system", "agent memory design", "long-running agent", "stateful agent", "agent that remembers", "MemGPT architecture", "Letta deployment", "/always-on-agent-architecture". NOT for: choosing what data to feed the agent (use always-on-agent-inputs), brainstorming applications (use always-on-agent-applications), safety and privacy concerns (use always-on-agent-safety), general agentic patterns (use agentic-patterns).

日本語の概要は準備中です。原文の説明を表示しています。

Prepare for Anthropic-specific technical interviews covering Constitutional AI, RLHF, interpretability, scaling laws, MCP, agentic systems, and AI safety. Activate on "anthropic interview", "constitutional AI prep", "alignment interview", "safety interview", "RLHF opinion", "interpretability prep", "anthropic technical". NOT for general ML interview prep, system design interviews, coding challenges, or behavioral interview practice.

日本語の概要は準備中です。原文の説明を表示しています。

Expert-level chemical process safety covering HAZOP, LOPA, relief system design, consequence modeling, inherently safer design, and process safety management.

日本語の概要は準備中です。原文の説明を表示しています。

Azure AI Content Safety SDK for Python. Use for detecting harmful content in text and images with multi-severity classification. Triggers: "azure-ai-contentsafety", "ContentSafetyClient", "content moderation", "harmful content", "text analysis", "image analysis".

日本語の概要は準備中です。原文の説明を表示しています。

Flags where a P&ID draft raises a process safety question and points to the candidate evidence an engineer would review (HAZOP register, relief study, SIL assessment, isolation philosophy), as questions and quoted passages with UNKNOWN for missing documents, plus safety functions, relief devices and isolation requirements carried over as stated. Never rates, sizes, classifies, resolves or declares protection adequate. Use when the user asks to "write the process safety flags", "produce the process safety section of the P&ID enrichment", "list which protection questions this P&ID raises" or "map the HAZOP and relief study evidence to the draft" after gate G2, once the piping and instrumentation sections exist. Do not use for proposing loops, alarms or trips from the control philosophy, use instrumentation-and-control-enrichment instead; do not use for checking identifiers, use tagging-and-numbering. Drafts for human review; never approves, authorises or signs off.

日本語の概要は準備中です。原文の説明を表示しています。

Autonomous AI code generation safety guardrail register: static AST analysis, forbidden import filters, and zero-day vulnerability checks.

日本語の概要は準備中です。原文の説明を表示しています。

Diagnose data races, convert callback-based code to async/await, implement actor isolation patterns, resolve Sendable conformance issues, and guide Swift 6 migration. Use when developers mention: (1) Swift Concurrency, async/await, actors, or tasks, (2) "use Swift Concurrency" or "modern concurrency patterns", (3) migrating to Swift 6, (4) data races or thread safety issues, (5) refactoring closures to async/await, (6) @MainActor, Sendable, or actor isolation, (7) concurrent code architecture or performance optimization, (8) concurrency-related linter warnings (SwiftLint or similar; e.g. async_without_await, Sendable/actor isolation/MainActor lint).

日本語の概要は準備中です。原文の説明を表示しています。

Comprehensive AI prompt engineering safety review and improvement prompt. Analyzes prompts for safety, bias, security vulnerabilities, and effectiveness while providing detailed improvement recommendations with extensive frameworks, testing methodologies, and educational content.

日本語の概要は準備中です。原文の説明を表示しています。

Comprehensive AI prompt engineering safety review and improvement prompt. Analyzes prompts for safety, bias, security vulnerabilities, and effectiveness while providing detailed improvement recommendations.

日本語の概要は準備中です。原文の説明を表示しています。

Implements content safety filters with PII redaction, policy constraints, prompt injection detection, and safe refusal templates. Use when adding "content moderation", "safety filters", "PII protection", or "guardrails".

日本語の概要は準備中です。原文の説明を表示しています。

Prepare for Anthropic-specific technical interviews covering Constitutional AI, RLHF, interpretability, scaling laws, MCP, agentic systems, and AI safety. Activate on "anthropic interview", "constitutional AI prep", "alignment interview", "safety interview", "RLHF opinion", "interpretability prep", "anthropic technical". NOT for general ML interview prep, system design interviews, coding challenges, or behavioral interview practice.

日本語の概要は準備中です。原文の説明を表示しています。

Kotlinのコード作成・レビュー・改修を支援します。nullの扱い、不変データ、非同期処理、型安全な設定記述を見直し、読みやすく保守しやすい構成に整えます。

• Kotlinのnull処理を点検したいとき
• 可変データや深い入れ子を整理したいとき
• コルーチンとFlowの非同期処理設計

医療アプリの公開前に、診療判断の支援ロジック、患者情報の漏えい、データ整合性などを検証するスキル。重大なテストの失敗でデプロイを止める仕組みを示します。

• 電子カルテの公開前に検証したいとき
• 薬物相互作用や投与量の変更を検証
• 権限変更後の患者情報漏えいを確認