85건 · 관련도순
Assessing privacy risks in large language model outputs including training data memorisation, PII leakage in generated text, prompt injection leading to data extraction, and hallucinated personal data. Covers output filtering, guardrails, and monitoring. Keywords: LLM privacy, output risk, memorisation, PII leakage, prompt injection, hallucinated PII.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Assess security risks in AI systems by scanning prompts for known attack patterns and scoring data exposure, poisoning, and tool abuse risks. Map findings to MITRE ATLAS, an AI threat framework, and identify protective controls.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Turn ePub books into training examples for models that reproduce an author's writing style. Covers text extraction, coherent segmentation, varied instructions, model training, and checks for copied phrases and style transfer to new scenarios.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Crawl linked pages within a chosen website scope and collect clean text, Markdown, or HTML with page metadata. Use the resulting records as source material for AI search systems or chatbot knowledge bases.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Select technologies for AI and machine learning features in .NET 8+ applications. Get task-specific plans or implementation guidance for structured predictions, text generation, document retrieval, tool-using agents, and running pretrained models locally or in production.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Extract sensitive training data and internal capabilities from AI models through repeated programmatic querying. Use this skill when testing LLMs and ML models for data privacy leaks, intellectual property exposure, or unintended memorization. Covers membership inference, prompt extraction, training data reconstruction, and API boundary testing.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Execute and analyze AI Data Poisoning attacks. By subtly injecting malicious or targeted misinformation into an LLM's training or fine-tuning dataset, an attacker can covertly manipulate the model's future outputs, implant backdoors, or enforce biases without altering the model architecture.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Curação de dados acelerada por GPU para treinamento de LLM. Suporta texto/imagem/vídeo/áudio. Recursos incluem deduplicação fuzzy (16× mais rápida), filtragem de qualidade (30+ heurísticas), deduplicação semântica, redação de PII, detecção NSFW. Escala em GPUs com RAPIDS. Use para preparar datasets de treinamento de alta qualidade, limpar dados web ou deduplicar grandes corpora.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Lambda Labs에서 GPU 서버를 시작하고 머신러닝 학습과 추론을 실행하는 절차를 안내합니다. SSH 연결, 영구 저장소, Python API 조작과 여러 GPU를 활용한 분산 학습도 다룹니다.
Builds LLM pretraining corpora from Common Crawl: extract, filter, deduplicate, decontaminate, mix, synthesize. Use when curating or ablating a pretraining corpus or data pipeline.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Train or fine-tune language and vision models using TRL (Transformer Reinforcement Learning) or Unsloth with Hugging Face Jobs infrastructure. Covers SFT, DPO, GRPO and reward modeling training methods, plus GGUF conversion for local deployment. Includes guidance on the TRL Jobs package, UV scripts with PEP 723 format, dataset preparation and validation, hardware selection, cost estimation, Trackio monitoring, Hub authentication, model selection/leaderboards and model persistence. Use for tasks involving cloud GPU training, GGUF conversion, or when users mention training on Hugging Face Jobs without local GPU setup.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
GPU-accelerated data curation for LLM training. Supports text/image/video/audio. Features fuzzy deduplication (16× faster), quality filtering (30+ heuristics), semantic deduplication, PII redaction, NSFW detection. Scales across GPUs with RAPIDS. Use for preparing high-quality training datasets, cleaning web data, or deduplicating large corpora.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Answer Python questions and write code using examples fetched from pythonsheets.com. Find patterns for syntax, asynchronous tasks, networking, databases, machine learning, and distributed computing, or use topic-based questions to prepare for Python interviews.
한국어 요약은 준비 중입니다. 영어 요약을 표시하고 있습니다.
Set up infrastructure for fine-tuning LLMs with QLoRA, LoRA, and full fine-tuning using Hugging Face TRL, Axolotl, and distributed training with DeepSpeed or FSDP. Covers dataset prep, training runs, and model export.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
You are an expert in Crawl4AI, the open-source web crawler built for AI applications. You help developers extract clean, structured data from websites for LLM training, RAG pipelines, and content analysis — with automatic markdown conversion, JavaScript rendering, CSS-based extraction, LLM-powered structured extraction, and session management for multi-page crawling.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Audit whether a paper's EVALUATION DESIGN actually measures what it claims and whether its reporting is complete — the validity layer family D (experiment-forensics) cannot reach. Three patterns: train/test leakage means the reported score may not measure generalization (HP-EVAL-LEAKAGE — adopts the Kapoor & Narayanan 8-type / 3-category leakage taxonomy; the illegitimate-proxy / sampling-bias / pretraining-contamination subtypes hand off as needs_external_check, naming but NEVER running Oren-2023 exchangeability / Shi-2023 Min-K% / Golchin-2023 Time-Travel / BIG-bench canary); a load-bearing LLM judge is conflicted (same model/family as a compared system) or unvalidated (no human-agreement, no bias control) (HP-JUDGE-VALIDITY); a declared condition/metric is dropped or switched to favor the method, or 'best' is chosen with no held-out set (HP-SELECTIVE-REPORTING). Verdict-bearing at L0/L1 from the DESCRIBED protocol — NOT repo-gated like experiment-forensics; L2 only CONFIRMS against split/preprocessing/result files. A fresh cross-model reviewer (gpt-5.6-sol xhigh, read-only, fresh thread per pass) PROPOSES findings, each span-anchored to a ledger claim_id; tools/adjudicate_findings.py DECIDES the verdict. Leakage and under-reporting are usually HONEST methodological errors — every finding describes a discrepancy to CHECK, never an accusation. An LLM generating GROUND-TRUTH labels is HP-FAKE-GT (experiment-forensics) — routed there, not here. Emits eval-design-forensics.findings.json; computes NO verdict. Detect-only. Triggers: "eval design audit", "evaluation validity", "train/test leakage", "data leakage", "is the score measuring generalization", "LLM judge bias", "is the judge validated", "selective reporting", "cherry-picked results", "评估设计审计", "评测有效性", "数据泄漏", "训练测试集泄漏", "裁判模型有没有验证", "选择性报告".
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Provides guidance for LLM post-training with RL using slime, a Megatron+SGLang framework. Use when training GLM models, implementing custom data generation workflows, or needing tight Megatron-LM integration for RL scaling.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
AI/LLM security offensive checklist: prompt injection, jailbreaking, model extraction, training data poisoning, adversarial inputs, LLM-assisted attack automation, and AI system reconnaissance. Use when assessing AI/ML systems, red-teaming LLMs, or researching AI attack vectors.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Unsloth로 언어 모델을 추가 학습하도록 돕습니다. LoRA와 QLoRA 구현, 기능과 API 확인, 코드 오류 조사, GPU 메모리를 줄이는 학습 방법 탐색을 지원합니다.
Guides technology selection and implementation of AI and ML features in .NET 8+ applications using ML.NET, Microsoft.Extensions.AI (MEAI), Microsoft Agent Framework (MAF), GitHub Copilot SDK, ONNX Runtime, and OllamaSharp. Covers the full spectrum from classic ML through modern LLM orchestration to local inference. Use when adding classification, regression, clustering, anomaly detection, recommendation, LLM integration (text generation, summarization, reasoning), RAG pipelines with vector search, agentic workflows with tool calling, Copilot extensions, or custom model inference via ONNX Runtime to a .NET project. DO NOT USE FOR projects targeting .NET Framework (requires .NET 8+), the task is pure data engineering or ETL with no ML/AI component, or the project needs a custom deep learning training loop (use Python with PyTorch/TensorFlow, then export to ONNX for .NET inference).
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Use AgileRL for reinforcement learning workflows: classical RL training, evolutionary HPO, evolvable networks, multi-agent PettingZoo training, offline/bandit data, and LLM fine-tuning.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Introduce people to AI, agentic AI, and AI skills with appropriate pedagogy for any audience. Covers LLM analogies, progressive complexity paths, aha-moment demos, audience-tailored explanations, workshop design, and overcoming emotional barriers to AI adoption. Activate on 'explain AI', 'introduce AI', 'AI workshop', 'AI demo', 'teach AI', 'AI literacy', 'onboard to AI', 'AI evangelism', 'explain agentic', 'explain skills to', 'AI training session', 'AI onboarding'. NOT for teaching ML engineering (use ai-engineer), not for building AI features (use ai-engineer), not for prompt engineering (use prompt-engineer), not for building training data pipelines.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.
Introduce people to AI, agentic AI, and AI skills with appropriate pedagogy for any audience. Covers LLM analogies, progressive complexity paths, aha-moment demos, audience-tailored explanations, workshop design, and overcoming emotional barriers to AI adoption. Activate on 'explain AI', 'introduce AI', 'AI workshop', 'AI demo', 'teach AI', 'AI literacy', 'onboard to AI', 'AI evangelism', 'explain agentic', 'explain skills to', 'AI training session', 'AI onboarding'. NOT for teaching ML engineering (use ai-engineer), not for building AI features (use ai-engineer), not for prompt engineering (use prompt-engineer), not for building training data pipelines.
한국어 요약은 준비 중입니다. 원문 설명을 표시하고 있습니다.