Study finds chatbots struggle to identify AI-generated images
11/19/2026 — 11/19, 02:19·1 sources (all)·1 reports (all)
Key takeaways
- A Brennan Center for Justice study asked six chatbots to determine whether an image generated by ChatGPT was AI-made. ChatGPT said it was li…
- only Gemini read OpenAI's hidden tag in the file. A mid-September retest after California's AI transparency law took effect showed no improv…
Background & analysis
On November 19, 2026, the AI section of DEV Community published a report drawing on research from the Brennan Center for Justice. In the study, researchers asked six chatbots to judge whether an image generated by ChatGPT, depicting a man standing next to a mailbox, was AI-made. ChatGPT examined the shadows, the hands, and the street sign in the picture and called it very likely genuine. Grok said that a real mailbox existed on that street in San Mateo, California. Claude guessed it was a stock photo, and Meta AI also called it real. Only Gemini managed to read the hidden OpenAI label carried in the file, the kind of label that California's AI Transparency Act has required. The report added that after the law took effect, the researchers ran a second round of tests in mid-September, and the results showed no improvement in any of the chatbots' judgments. The public record of this matter currently rests at that follow-up round of testing, with no further developments reported since.
AI-generated from 1 reports · updated 3 days ago
- Heat index
- 25
- All sources
- 1
- All reports
- 1
- First seen
- 3 days ago
Reports on this story headlines open the original
Researchers at the Brennan Center for Justice asked six chatbots whether an image made by ChatGPT was AI-generated; ChatGPT called it very likely genuine, Grok, Claude and Meta AI also got it wrong, and only Gemini read the hidden OpenAI label in the file. A mid-September rerun after California's AI Transparency Act took effect found no improvement.
DEV Community · AIAI score 58
Other stories people are talking about
- Heat index 1143RisingAnthropic Reaches $1.6 Trillion Market Value in First Trading Week After IPO21 sources
- Heat index 1011Anthropic Mathematician Says Claude Formalized the Generalized Riemann Hypothesis21 sources
- Heat index 622Anthropic IPO total raise reaches $93.5 billion after greenshoe exercise20 sources
- Heat index 596RisingThinking Machines Lab Open-Sources Inkling 2 Mini with 32GB Model Card Recommendation10 sources
- Heat index 490RisingSEC probes Nvidia accounting practices as shares post seven-week slide9 sources
How is heat calculated?About the methodHide
Heat counts how many independent sources covered a story in the last 48 hours: one source counts once no matter how many posts it published, decaying with a 24-hour half-life. What ranks first is what many people are talking about.
This page aggregates public feeds. Headlines and summaries are machine-organized and remain the property of the original authors; verify important facts at the source. If you believe a headline or summary infringes your rights, email the contact address in the footer with the page URL and basis of your claim, and we will remove or replace it after review.
- Surge
- Discussion rising fast
- New
- First report within 6 hours
- Rising
- Still gathering discussion

