Get the latest tech news

My 8 ChatGPT Agent tests produced only 1 near-perfect result - and a lot of alternative facts


Can ChatGPT Agent replace your assistant? No, and my in-depth testing proves it. Here's what it can - and can't - do.

Screenshot by David Gewirtz/ZDNET Understanding of the problem: Solid Execution: Added the correct data point Hallucination: Was unable to reproduce graphic quality Processing time: 10 minutes When I told it to use the web interface, it started to, but it reported, "Unfortunately, I've reached the end of the allotted browsing sessions for this task, which means I'm unable to explore further pages and collect the additional data at this time." In any case, Agent did give me back a spreadsheet and a slide based on the limited data it was able to find before my little request exceeded the hourly power budget for the City of Las Vegas (or so I imagine).

Get the Android app

Or read this on ZDNet

Read more on:

Photo of lot

lot

Photo of alternative facts

alternative facts

Photo of perfect result

perfect result

Related news:

News photo

As companies race to add AI, terms of service changes are going to freak a lot of people out

News photo

U.S. Power Utilities Seek Price Hikes Due to Increased AI Data Center Demand -- a 142% increase since 2024. "A lot of states don’t have a playbook for how they can meet rising [data centre] demand while balancing affordability and utility bills.”

News photo

Sloclap reveals surprising Rematch player data that explains a lot about this summer hit