AI Safety & Ethics

Anthropic is an AI company that provides the Claude family of large language models and a developer platform, distributi…

Guardrails are a runtime control layer that intercepts and validates LLM inputs and outputs against safety, security, an…

Hallucination is a failure mode where an LLM produces fluent content that conflicts with source evidence, real-world fac…

OpenAI is an AI platform and API provider that offers models such as GPT‑5.5 and hosted tools to developers, exposing a …

Prompt injection is an attack that causes an LLM application to treat untrusted user input or external content as higher…

A safety incident is a reportable AI event in which system behavior causes harm, enables misuse, exposes sensitive infor…

A supply-chain attack is an indirect compromise that targets upstream components and trust relationships in the software…