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

Adam Mosseri acknowledges ‘mistakes’ in Threads’ broken moderation


Head of Instagram Adam Mosseri is acknowledging recent mistakes in Meta’s moderation processes on Threads and Instagram. For example, Meta unexpectedly deleted my account this week because it thought I was underage, the company locked my colleague’s account because she joked about dying in a heatwave, and others have seen their posts disappear with no clear reason why. “Threads Moderation Failures” has been trending this week — putting more pressure on Meta’s moderation processes.

Now Mosseri admits that Meta is having problems with those processes and has publicly posted that acknowledgment on Threads. He explains there’s a “tool” that broke, which apparently did not show human reviewers “sufficient context” before they made posts and accounts disappear. You might think Meta is using AI to make decisions on what to delete and who to ban, but Mosseri’s suggesting that’s still done by humans and that the algorithm is just flagging posts for possible enforcement actions.

Meta is already fixing some of the mistakes it found, according to Mosseri, helping reviewers make better calls in the future. “We need to do better,” Mosseri wrote.

Things already seem better for me, personally: Meta quietly reinstated my account yesterday. But Meta didn’t answer our questions about why users’ posts and accounts were being deleted. For me, the whole appeal process was grueling and mentally exhausting, as I explained in detail on Wednesday.



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