#anthropic

Rascunho de traducao automatica (Portuguese) for "MCP": Model Context Protocol - An open standard developed by Anthropic for connecting AI assistants to external tools, data sources, and services. Enables AI agents to interact with the world in standardized ways.

“Exemplo em rascunho: Our platform exposes all its APIs via MCP so any AI assistant can integrate with it.”

Rascunho de traducao automatica (Portuguese) for "Constitutional AI": A training methodology developed by Anthropic where a set of guiding principles (a "constitution") is used to self-supervise and refine AI outputs. The model critiques and rewrites its own responses according to the constitution, reducing the need for human labelers for harmful content.

“Exemplo em rascunho: Constitutional AI lets the model identify and self-correct its own harmful outputs using defined principles.”