OpenAI’s artificial intelligence (AI) chatbot ChatGPT will predict the age of its users to give teenagers a safer online experience, as scrutiny grows about how tech companies protect minors online.
The company’s new age prediction systemwill use information about a user’s account to predict whether that person is under 18, such as how long the account has existed, the times of day that they log on, and how they use the app.
When ChatGPT identifies a user under 18, additional protections against graphic, violent, self-harm, and sexual content will immediately be turned on. Viral social media challenges that encourage “risky or harmful behaviour” for minors will also be limited.
OpenAI said this approach is “guided by expert input and rooted in academic literature about the science of child development.”
Accounts identified as belonging to those under the age of 18can still use ChatGPT to learn, create, and ask questions, the company said.
The OpenAI update comes as governments in the European Union are discussing restrictions on social media accounts for users under 16, after Australia enacted a banin December. ChatGPT is not considered a social media platform under Australia’s restrictions.
OpenAI and its CEO, Sam Altman, are being sued in California by the parents of 16-year-old Adam Raine, who committed suicide last April, after the platform allegedly coached him to take his life and wrote a suicide note for him.
OpenAI previously introduced parental controls on ChatGPT that allow parents to set “quiet hours” where the AI can’t be used and to receive notifications if their teen shows any signs of distress during their messages with the AI bot.
Anyone falsely identified as under 18 in the new system will be able to take a live selfie or upload a government ID to verify their age and have the restrictions lifted.
