5 AI bots took our tough reading test. One was smartest — and it wasn’t ChatGPT.

We challenged AI helpers to decode legal contracts, simplify medical research, speed-read a novel and make sense of Trump speeches. Some of the AI analysis was impressive — and some was downright dumb.

9 min
Robots reading while a robot referee blows a whistle.
(Illustration by Johanna Walderdorff/For The Washington Post)
Skip to main content
Review by

All of the most popular artificial intelligence chatbots have the ability to upload and summarize documents, from legal contracts to an entire book. The tech promises to give you a kind of speed-reading superpower. But do any of the bots really understand what they’re reading?

Get concise answers to your questions. Try Ask The Post AI.

To figure out which AI tools you can trust as a reading assistant, I held a competition. I challenged five bots to read four very different types of writing and then tested their comprehension. The reading spanned the liberal arts, including a novel, medical research, legal agreements and speeches by President Donald Trump.

Help Desk: Making tech work for you

Help Desk is a destination built for readers looking to better understand and take control of the technology used in everyday life.

Take control: Sign up for The Tech Friend newsletter to get straight talk and advice on how to make your tech a force for good.

Tech tips to make your life easier: What to know about what’s new in iOS 18.2 | 5 tips to make your gadget batteries last longer | How to get back control of a hacked social media account | Meta ends fact-checking | The best tech to have in a natural disaster

Tech trends: The best and weirdest tech at CES 2025 | Tech trends to watch in 2025

Data and Privacy: A guide to every privacy setting you should change now. We have gone through the settings for the most popular (and problematic) services to give you recommendations. Google | Amazon | Facebook | Venmo | Apple | Android

Ask a question: Send the Help Desk your personal technology questions.

Show more

What readers are saying

The comments reflect a general skepticism about the reliability and accuracy of AI, particularly in high-stakes situations. Many users express concerns about AI's tendency to "hallucinate" or fabricate information, highlighting the need for human oversight and verification. There... Show more
This summary is AI-generated. AI can make mistakes and this summary is not a replacement for reading the comments.
By
Geoffrey A. Fowler is The Washington Post’s technology columnist based in San Francisco. He joined The Post in 2017 after 16 years with the Wall Street Journal. He won the 2020 Gerald Loeb Award for commentary.@geoffreyfowler
NewsletterAs news breaks
Tech News Alerts
Breaking news email alerts on technology and the tech industry.
NewsletterAs news breaks
Tech News Alerts
Breaking news email alerts on technology and the tech industry.
Already have an account?

Two ways to read this article:

Create an account
Free
  • Access this article
Enter email address
By selecting "Start reading," you agree to The Washington Post's Terms of Service and Privacy Policy.
Subscribe
$4 USDevery 4 weeks for the first year
  • Unlimited access to all articles
  • 24/7 live news updates