Glossary term
Glossary term
Safety and Alignment
Augmentation enriches AI models with external context, real-time data, or tools to produce more accurate, relevant outputs, turning general-purpose models into domain-aware, task-specific assistants without retraining.
Bloomberg GPT augments general LLM outputs with proprietary financial data and news for terminal users.
Harvey AI augments base models like GPT-4 with legal precedent and firm-specific documents for law firms.
Perplexity augments responses with real-time web search and citations rather than relying solely on pre-trained knowledge.