I asked the Claude Large Language Model to compare two Trump news conference transcriptions: September 27, 2020 and April 6, 2026. It concluded that a comparison of Trump’s unscripted and impromptu words showed detectable cognitive decline during those six years.
Claude reported, “This is the most striking quantitative finding. The 2026 speech has nearly 3× more mid-sentence interruptions relative to word count. This reflects a significantly higher rate of losing the thread, restarting, or abandoning clauses — a known linguistic marker researchers associate with cognitive aging.” Full Claude Report
Project Structure, methods and sources. Why and how I did this comparison, why I trusted the generally inaccurate and hallucinating Claude LLM engine’s results and why it isn’t TDS.
Claude Finds Trump Cognitive Decline
July 5, 2026
Comments
I think you found a very appropriate and useful application of the Claude model. You assigned it grunt work, not creative tasks, and you were able to check and verify its work. I hope that once we all learn how to use (and not use) AI models, this will be the kind of labor saving help that will enhance our productivity.