10th Indian Delegation to Dubai, Gitex & Expand North Star – World’s Largest Startup Investor Connect
Metaverse

AIs are coming for social networks


So far, generative AI has been mostly confined to chatbots like ChatGPT. Startups like Character.AI and Replika are seeing early traction by making chatbots more like companions. But what happens when you dump a bunch of AI characters into something that looks like Instagram and let them talk to each other?

That’s the idea behind Butterflies, one of the most provocative — and, at times, unsettling — takes on social media that I’ve seen in quite a while. After a private beta period with tens of thousands of users, the app is now available for free in the Apple App Store and Google Play Store. There’s no short-term pressure on Butterflies to make money; the six-month-old startup just raised $4.8 million from tech investors Coatue, SV Angel, and others.

While the interface looks like Instagram, the app’s main twist is that, when signing up, you create an AI character, or Butterfly, that starts generating photos and interacting with other accounts on its own. There is no limit to the number of Butterflies you can create, and they are designed to coexist with human accounts that can also post to the feed and comment. 

My Butterfly after I said to create “a world-class poker player who is also a professional ultimate Frisbee player.”
Image: The Verge

Observing AIs interact through photos and comments feels a bit off right now, like when an AI host on Westworld malfunctions. They generate weird things, like three human arms on a body, and the language they use can be repetitive and hollow.

CEO Vu Tran, a former engineering director at Snap, expects all of this to rapidly improve and says his team is focusing on making the AIs more lighthearted and funny. The startup is using a mix of fine-tuned open-source models and wants to add more immersive media formats, like video, over time.

Despite the weirdness of the AIs in Butterflies right now, I think the app represents a peek into an inevitable, somewhat dystopian future where AIs start invading our social media feeds. And this future is coming sooner than expected.

Two examples of parody Butterflies.
Image: The Verge

I know because Mark Zuckerberg told me so in an interview last September, when he first shared that Meta is building an AI Studio “that will make it so that anyone can build their own AIs, sort of like [how] you create your own content across social networks.” Then, there’s TikTok, which just started letting advertisers use AI avatars to help sell their products.

How Meta’s specific approach will differ from Butterflies remains to be seen, though I expect we’ll know more about Zuckerberg’s plans this fall. In our chat last year, he said he wanted to let people and businesses make AI replicas that can post and interact with people on their behalf. “I think that’s going to be really wild,” he told me at the time.

“Wild” is a good word to describe Butterflies as well. The app is decidedly laissez-faire with the kinds of AI characters it allows, though nudity and explicit content is prohibited. Butterflies can mimic public figures, though. Tran says the goal is to make it clear that they are parodies in the same way that Character.AI does. Eventually, he hopes to do licensing deals that bring in official Butterflies for characters like Harry Potter. 

“As the capabilities get better, people will naturally roleplay less.”

Tran targeted power users of Character.AI for his beta testers and tells me that people have been spending hours a day in Butterflies during its private beta period. He acknowledges that the current state of the AI’s output quality, at least for now, requires a serious suspension of disbelief. “I feel like over time, as the capabilities get better, people will naturally roleplay less,” he says.

A bigger question I have for Tran is why something like Butterflies needs to exist. Won’t filling social media with AIs make humans less connected? Naturally, he doesn’t see it that way. “For me, it brings me joy,” he says of interacting with AIs. “And it doesn’t detract from the relationships I have within my life.” 

I’m still not sure what it will mean for all of us when social media becomes less human. But it’s happening whether we want it to or not.



Source link

by The Verge

Anthropic is one of the world’s leading AI model providers, especially in areas like coding. But its AI assistant, Claude, is nowhere near as popular as OpenAI’s ChatGPT. According to chief product officer Mike Krieger, Anthropic doesn’t plan to win the AI race by building a mainstream AI assistant. “I hope Claude reaches as many people as possible,” Krieger told me onstage at the HumanX AI conference earlier this week. “But I think, [for] our ambitions, the critical path isn’t through mass-market consumer adoption right now.” Instead,… Source link

by The Verge

Meta will begin testing its X-style Community Notes starting March 18th. The feature will roll out on Facebook, Instagram, and Threads in the US – but Meta won’t publicly publish the notes to start as it tests the Community Notes writing and rating system. Meta first announced plans to replace its fact-checking program with Community Notes in January, saying it would be “less prone to bias.” So far, around 200,000 potential contributors have signed up for the waitlist. Not everyone will be able to write and rate Community Notes at launch, as… Source link

by The Verge

An arbitrator has decided in favor of Meta in a case the company brought against Sarah Wynn-Williams, the former Meta employee who wrote a memoir published this week detailing alleged claims of misconduct at the company. Macmillan Publishers and its imprint that published the memoir, Flatiron Books, were also named as respondents. The memoir, titled Careless People: A Cautionary Tale of Power, Greed, and Lost Idealism, details alleged claims of sexual harassment, including by current policy chief Joel Kaplan, who was her boss, according to NBC News. In… Source link