News

It’s Laughably Easy to Poison Open-Weight AI Models, Researcher Finds

  • Frank Landymore--Futurism
  • published date: 2026-07-19 12:00:00 UTC

"I did a proper backdoor." The post It’s Laughably Easy to Poison Open-Weight AI Models, Researcher Finds appeared first on Futurism.

Can’t-miss innovations from the bleeding edge of science and tech Good news, everyone: “open-weight” AI models that are available to anyone to download and run are comically easy to poison. Katie P… [+2870 chars]