When Summaries Sail and Citations Sink: Lessons from Gemini and Perplexity Failures

https://www.cool-bookmarks.win/claude-opus-4-6-vs-gpt-5-2-which-model-should-you-trust-for-legal-analysis

How a 0.7% Summarization Error Turned into an 88% Hallucination Nightmare The data suggests a stark divergence in behavior across seemingly related AI models. In staged evaluations I ran: Gemini 2