When a 2022 Hallucination Burn Came Back: Comparing GPT-4.1 and GPT-5 After Gemini 2.0 Flash’s 0.7% Claim

https://ricardosmasterchat.lucialpiazzale.com/why-ctos-and-engineering-leads-struggle-to-pick-models-for-production-when-hallucinations-can-harm-people

How a biased vendor claim forced a product team to retest summarization models In 2022 our team implemented GPT-3.5 for summarization tasks inside a legal-document intake pipeline