Skip to main content
  1. Home
  2. Computing
  3. Legacy Archives

IBM’s Watson supercomputer beats humans in Jeopardy

Add as a preferred source on Google

Its may only have been a practice match, but Watson has proven to be a serious competitor to the likes of Jennings and Rutter. Watson is IBM’s Jeopardy-playing supercomputer. And Ken Jennings and Brad Rutter — both Jeopardy champions — served as human competition today during a preliminary Jeopardy match with the machine.

IBM took four years to develop the supercomputer so that it would be capable of mastering the subtleties of the language-based trivia that defines Jeopardy. To get Watson at the Jeopardy-smart level, engineers scanned over 200 million pages of information into its memory.

Recommended Videos

Watson, named after IBM founder Thomas J. Watson, is made up of 10 racks of IBM Power 750 servers and runs Linux as its operating system. It also has 15 terabytes of RAM, and 2,880 processor cores. That makes Watson able to scan the millions of pages of data stored in its memory in a quick three seconds. Oh, and it won’t fit on a desktop — it’s the size of 10 refrigerators.

Watson is considered to be the next big step forward in artificial intelligence that could soon be applied to areas outside of games. Watson’s creators suggest the machine’s abilities may be useful in the health care industry in the future. In 1997, IBM supercomputer Deep Blue defeated Gary Kasparov in a chess match that ignited the public’s fascination in human-computer competition.

Despite some categories that seemingly only a human could comprehend (“Chicks Dig Me” for one), Watson triumphed in today’s practice round, but not by enough to signal an imminent Watson is ready to lead machines in a world-takeover. Watson finished with a score of $4,400 and Jennings came in second place with $3,400 and Rutter was last with $1,200.

Today’s practice round held in Yorkston Heights, New York set the stage for a series of Jeopardy matches with Watson to be held in February.

In this video, IBM explains why they chose Jeopardy to test its latest supercomputer.

Aemon Malone
Former Digital Trends Contributor
AI may have just won a literary prize. My heart weeps seeing it poison our love for books.
updated book and AI photo

I had a hard time processing this news. As someone who has been deeply in love with stories since childhood and who grew up on the works of Arthur Conan Doyle, Terry Pratchett, J.R.R. Tolkien, and other such venerable authors, seeing an AI-written story win a prestigious writing award is hard to digest. 

If you are unaware, the winners for the Commonwealth Short Story Prize for 2026 were announced, and three of the five winning regional stories have been found to be entirely or partially written by AI. Or at least that seems to be the consensus among readers. As a reader and an amateur fiction writer, this hurt me deeper than any other tale of AI corroding our lives.

Read more
Canva and Adobe are coming to Gemini, and they want to make everything chatty
Adobe and Canva are plugging into Google’s assistant, betting that creative work starts with a prompt, not an app icon
Art, Collage, Photography

Canva and Adobe are moving deeper into Google Gemini, giving the assistant a bigger role before users ever open a design app.

Adobe says its "Adobe for creativity" connector is coming to Gemini in the coming weeks, giving users a way to describe tasks and send them through Adobe tools for imaging, design, and video. Canva is already rolling out its Connected App for Gemini in select English-language markets, with full availability coming soon.

Read more
AI can pass the Turing Test in live chats and appear more human than us. I am spooked now
UC San Diego researchers found GPT-4.5 was judged human 73% of the time in live conversations
Image of a human woman next to an AI-generated face with Real or Fake text at the bottom.

AI can pass the Turing Test in live chats, and the latest result lands with a chill. In a UC San Diego study, GPT-4.5 outperformed real participants at convincing judges there was a person on the other side.

The setup was harder to shrug off than a standard benchmark. Judges reacted to real-time exchanges rather than static prompts, then made a fast call based on conversation alone.

Read more