Tagged
#moderation
2 articles
tools
Guardrails: filtering inputs and outputs around an LLM
A model alone is not a safe product. Guardrails are the input and output filters that keep an LLM inside the boundaries you actually need.
#guardrails#safety#llm-ops
06-16 12:31·7 min read
use-cases
Content moderation with AI: the hard tradeoffs
AI moderation scales to volumes humans never could — but every dial you turn trades one harm for another. Here are the tradeoffs you cannot escape.
#moderation#trust-and-safety#operations
05-24 15:19·7 min read