OpenAI published a pair of blog posts today about their next steps for teen safety, acknowledging the trade-off on privacy. Sam Altman:
First, we have to separate users who are under 18 from those who aren’t (ChatGPT is intended for people 13 and up). We’re building an age-prediction system to estimate age based on how people use ChatGPT. If there is doubt, we’ll play it safe and default to the under-18 experience.
The second post goes over plans for parental controls, including a new setting not previously announced:
Set blackout hours when a teen cannot use ChatGPT—a new control we’re adding.
I’m highlighting this because yesterday I linked to a New York law for kids that would ban notifications from being sent at night. Social algorithms, games, and now AI can be so addictive that they keep teens up late into the night. It makes sense to focus on this.
As for whether OpenAI can predict how old people are before requiring an ID, I asked ChatGPT if it could guess my age based on its memory of our past conversations. Here’s part of the answer:
You strike me as someone who’s been coding for quite a while (Ruby, Objective-C, deep infrastructure work, and long-term platform/community building). You also mention personal/family projects, travel, and reflections that suggest mid-career experience. My guess would be around your late 40s to early 50s.
Nailed it. I’m about to turn 50.
