Me tl;dr-ing:: Summarizing using LLMS is good when volume is a good predictor of importance which isn't often the case. Still true in 2025? May 2024:: Gerben Wierda::: When ChatGPT summarises, it actually does nothing of the kind. – R&A IT Strategy & Architecture
Discovered: Feb 9, 2025 07:48 Me tl;dr-ing:: Summarizing using LLMS is good when volume is a good predictor of importance which isn’t often the case. Still true in 2025? May 2024:: Gerben Wierda::: When ChatGPT summarises, it actually does nothing of the kind. – R&A IT Strategy & Architecture
QUOTE:
- Read the whole thing: When ChatGPT summarises, it actually does nothing of the kind. – R&A IT Strategy & Architecture
So, when will shortening the text be good enough for a reliable summary? Probably only when summarising consists of nothing else than turning something unnecessarily repetitive and long-winding into something short, i.e. when volume is a good predictor of importance. That is far less of a use case than people think. In the meantime, the result itself will — errors and all — suggest to readers that it is a true and reliable summary and we’re not going to doubt that, human as we are.