OpenAI’s latest AI video generator Sora 2 has gotten a lot of attention for its realistic creations. The tool is supposed to have guardrails to prevent creating videos based on misinformation.

But new analysis from watchdog group Newsguard found that, when prompted, Sora 2 often generated videos based on lies, such as false claims having to do with election fraud in a foreign country or that a toddler was detained by immigration agents.

Marketplace’s Nova Safo spoke with Sofia Rubinson, senior editor at Newsguard, to learn more.