Content creators are busy people. Most spend more than 20 hours a week creating new content for their respective corners of the web. That doesn’t leave much time for audience engagement. But Mark Zuckerberg, Meta’s CEO, thinks that AI could solve this problem.
In an interview with internet personality Rowan Cheung, Zuckerberg laid out his vision for a future in which creators have their own bots, of sorts, that capture their personalities and “business objectives.” Creators will offload some community outreach to these bots to free up time for other, presumably more important tasks, Zuckerberg says.
“I think there’s going to be a huge unlock where basically every creator can pull in all their information from social media and train these systems to reflect their values and their objectives and what they’re trying to do, and then people can can interact with that,” Zuckerberg said. “It’ll be almost like this artistic artifact that creators create that people can kind of interact with in different ways.”
Zuckerberg’s thinking is common in many techno-optimist circles: that AI is an inherent good because it promises to vastly scale up the impact a single person — or organization — can have. (Google, too, has pitched AI-powered tools for creators.) But when productivity comes at the expense of the personal touch, would creators, whose audiences value authenticity, really be the ones to embrace generative AI?
Not helping Zuckerberg’s case, Meta hasn’t exactly delivered a strong sales pitch.
When Meta began to roll out AI-powered bots as a part of its broader Meta AI push earlier this year, it didn’t take long for the bots to fall prey to the many pitfalls of today’s generative AI tech, in particular hallucinations. The Associated Press observed one bot inserting itself into a conversation in a Facebook group for Manhattan moms and claiming it had a child in the NYC school district. Another bot offered to give away a nonexistent camera and A/C in a forum for swapping free items near Boston.
To be fair, Meta’s AI is improving — or so the company claims, at least. The latest release, the Llama 3.1 model family, which will power a number of features across the tech giant’s platforms, is Meta’s most sophisticated yet judging by the benchmarks. But hallucinations — and general mistakes in planning and reasoning — remain an unsolved problem in generative AI, and Meta offers no research breakthroughs there.
