Results for “knowledge-base-poisoning”

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.

Build and query AI-powered knowledge bases from claude-mem observations, enabling focused conversational sessions on specific topics.

Karpathy's LLM Wiki: build/query interlinked markdown KB.

Use to audit a help centre or knowledge base against the conversations customers actually have, finding coverage gaps, stale articles and unused content. Trigger for "what should we write help articles about", "audit our knowledge base", KB coverage gaps, self-service deflection content, or preparing a knowledge base to ground an AI support agent.

Detect poisoned training data and backdoored models across the ML pipeline using statistical analysis, activation clustering, and spectral signatures.

Karpathy's LLM Wiki: build/query interlinked markdown KB.

Manage a multi-layered knowledge system for ingesting, organizing, syncing, and retrieving knowledge across local files, MCP memory, vector stores, and Git repos.

Karpathy's LLM Wiki — build and maintain a persistent, interlinked markdown knowledge base. Ingest sources, query compiled knowledge, and lint for consistency.

Turns a local folder into a searchable, maintainable knowledge base for AI agents, handling setup, navigation, content ingestion, querying, and health checks without external databases or RAG systems.

Karpathy's LLM Wiki: build/query interlinked markdown KB.

Karpathy's LLM Wiki: build/query interlinked markdown KB.

Karpathy's LLM Wiki: build/query interlinked markdown KB.

跨多个存储层（本地文件、MCP memory、向量存储、Git 仓库）的知识库管理、摄取、同步和检索。在用户想要保存、组织、同步、去重或跨知识系统搜索时使用。

Karpathy's LLM Wiki — build and maintain a persistent, interlinked markdown knowledge base. Ingest sources, query compiled knowledge, and lint for consistency.