The tag 'rag and ai' covers retrieval-augmented generation (RAG) as applied to archival content and AI authority. Discussions focus on how feeding old archives into AI models, such as Microsoft Copilot, can transform historical disputes into new evidence engines. The content highlights risks where AI output, especially legal-sounding memos, gains unearned authority. Recurring themes include the use of RAG to pair archive material with chatbots, the shift from satire to machine-readable input, and the operational changes generative AI introduces to existing disputes. This tag is relevant for those exploring RAG implementations, AI trustworthiness, and the intersection of legacy data with modern language models.
-
The May 16, 2026 Royaldutchshellplc.com post republished a WindowsForum-style analysis of John Donovan’s late-December AI experiment, in which Shell-related archive material was fed to multiple chatbots and paired with a Microsoft Copilot defamation-risk memo. The episode is not just another...