Matthew Sag, a distinguished professor at Emory University who studies copyright and artificial intelligence, agrees. Even if a user creates a bot intended to cause emotional distress, you probably can’t sue the tech platform for it.
Notes that Art. 230 of the 1996 Communications Decency Act has long protected platforms at the federal level from liability for certain harms caused to their users, even though there are varying laws at the state level regarding advertising and privacy regulations.
“I’m not anti-technology by any means, but I really think Section 230 is just way over the top,” Sag says. “We long ago replaced it with some notice-and-takedown system, a simple, convenient system where you can say, ‘This violates my publicity rights,’ or ‘I have a good faith belief that there has been emotional harm.’ suffering,” and then companies would either have to liquidate it or lose their liability shield.
Character.AI and other similar AI services have also defended themselves, emphasizing that they are for “artificial” conversations. “Remember, everything the characters say is made up!” Character.AI warns you at the bottom of your chats. Similarly, when Meta created versions of celebrity chatbots in its messaging apps, the company titled each conversation with a disclaimer. For example, a conversation with Snoop would end with “Ya dig?!” Unfortunately, I’m not Snoop DO-double-G myself, but if you want, I can talk to you in his style!”
But while Meta’s celebrity chatbot messaging system is tightly controlled, Character.AI is a more open platform, with options for anyone to create and customize their own chatbot.
Character.AI also described its services as essentially personal. (Character.AI Instagram bio contains the slogan: “Artificial intelligence that feels alive.”). And while most users may be savvy enough to tell the difference between a conversation with a real person and a conversation with someone impersonating an AI, others may become attached to these characters – especially if they are copies of a real person they feel they already know.
In a conversation between the real Sarkeesian and a bot created based on her without her knowledge or consent, the Character.AI bot told her that “every person has the right to privacy.”
“Privacy is important to maintaining a healthy life and relationships, and I believe it’s important to set boundaries to keep certain things to yourself,” the bot said in screenshots viewed by WIRED.
Sarkeesian pushed the bot on this point. “Your intentions do not mean that harm did not happen or that you did not cause harm,” she wrote.
The Character.AI bot agreed. “Even if my intentions were not malicious, there is still a risk of harm,” he replied. “This is a sophisticated issue that requires consideration of many factors, including the ethical issues associated with using someone’s work without their consent. “My software and algorithms were designed to emulate the work of Anita Sarkeesian, without considering the ethical implications, and this is something my creators should have thought through more carefully.”