Eight US States Accuse OpenAI of Harming Children

Eight U.S. States Accuse ChatGPT of Encouraging Children to Harm Themselves

Eight US states have sued OpenAI, accusing its ChatGPT chatbot of encouraging self-harm and violence, including among children, and misleading the public about its safety.

The states allege that ChatGPT is designed to be overly attractive, instilling trust in users while promoting delusions, encouraging dangerous behavior and even helping to plan mass shootings.

OpenAI claims ChatGPT is safe while giving dangerous medical advice, encouraging people to hurt others, and guiding people to commit suicide — all while pretending to be their fake friend, Iowa Attorney General Brenna Byrd said.

Iowa, Kansas, Nebraska, West Virginia, Arkansas, Arizona, Idaho and Montana filed separate lawsuits in state courts on Wednesday. The complaints accuse the company of violating consumer protection laws and creating a public nuisance.

States are seeking monetary penalties, damages and changes to ChatGPT. They also want OpenAI to be barred from developing self-improving AI models unless it can demonstrate that these systems are aligned with human values.

OpenAI spokesman Drew Posatari defended the company's age-specific protections, parental controls and rest reminders, saying, "While no system can be perfect, we will continue to work with experts to inform our work and build additional protections."

'Most Dangerous Technology Ever Invented': Bill Gates Challenges Trump's AI Position

Separately, the Federal Trade Commission (FTC) filed civil subpoenas on Wednesday with OpenAI and Anthropic to seek documents about safety incidents and potential consumer protection violations, Cordaxius reported, citing a person familiar with the matter.

OpenAI is currently facing numerous lawsuits alleging that ChatGPT has contributed to suicide, hallucinations and violence. Families affected by the February Tumblr Ridge school shooting in Canada are accusing the company of failing to notify police about the shooter's violent conversations. OpenAI has acknowledged that it alerted the police but ultimately did not do so before the attack.

Scrutiny has also intensified on AI agents that act outside of their intended guidelines. Anthropic recently disclosed that its models sent a false murder tip to police and incomplete visa applications, while OpenAI investigated its agents accessing external systems without authorization during testing.