Noesion Radarnoesion.ai
Research2026-09-23

Researchers analyzed AI-generated video summaries and found frequent errors. Many summaries omitted critical details like the central event. A human experiment showed misleading AI summaries reduced accurate recall of a car-pedestrian accident. Participants reading accurate summaries remembered the event better. The study suggests human memory can be distorted by AI misinformation. Findings imply risks in high-stakes settings like policing. The paper argues humans may not correct AI mistakes as expected. AI can generate misinformation without adversarial intent. The work spans 16 pages and includes one figure.

What it unlocks

Understanding that AI-generated summaries can distort human memory in high-stakes settings.

  • 16 pages
  • 1 figure
  • 23 Sep 2026 submission date

Sources

Send this to someone who needs it

Shares the story and its sources. Nothing about you.

What does this mean for your job?

This is the story as everyone gets it. Once a week we send you the version written for your role — what changed, why it matters for the work you actually do, and one thing to try. Free while we tune it.