Hackers aim to find flaws in AI — with White House help

, and other major AI providers such as Google and Microsoft, are coordinating with the Biden administration to let thousands of hackers take a shot at testing the limits of their technology.

Anyone who’s tried ChatGPT, Microsoft’s Bing chatbot or Google’s Bard will have quickly learned that they have a tendency to fabricate information and confidently present it as fact. These systems, built on what’s known as large language models, also emulate the cultural biases they’ve learned from being trained upon huge troves of what people have written online.

There’s already a community of users trying their best to trick chatbots and highlight their flaws. Some are official “red teams” authorized by the companies to “prompt attack” the AI models to discover their vulnerabilities. Many others are hobbyists showing off humorous or disturbing outputs on social media until they get banned for violating a product’s terms of service.

In another example, searching for Chowdhury using an early version of Microsoft’s Bing search engine chatbot — which is based on the same technology as ChatGPT but can pull real-time information from the internet — led to a profile that speculated Chowdhury “loves to buy new shoes every month” and made strange and gendered assertions about her physical appearance.

Chowdhury, now the co-founder of AI accountability nonprofit Humane Intelligence, said it’s not just about finding flaws but about figuring out ways to fix them. “As these foundation models become more and more widespread, it’s really critical that we do everything we can to ensure their safety,” said Scale CEO Alexandr Wang. “You can imagine somebody on one side of the world asking it some very sensitive or detailed questions, including some of their personal information. You don’t want any of that information leaking to any other user.”

United States Latest News, United States Headlines

Similar News:You can also read news stories similar to this one that we have collected from other news sources.

Hackers aim to find flaws in AI — with White House helpNo sooner did ChatGPT get unleashed than hackers started “jailbreaking” the artificial intelligence chatbot – trying to override its safeguards so it could blurt out something unhinged or obscene.
Source: wjxt4 - 🏆 246. / 63 Read more »

Hackers look for AI flaws under White House directionA mass hacking event will target models from OpenAI, Microsoft and more, looking for flaws in AI systems at the direction of the White House.
Source: FoxBusiness - 🏆 458. / 53 Read more »

White House rips House Oversight Republicans before press conference: 'Absurd claims'The White House said GOPoversight Chairman RepJamesComer's highly anticipated press conference about his panel's investigation into alleged influence peddling by POTUS's family the latest example of Comer's 'long pattern of making absurd claims.'
Source: dcexaminer - 🏆 6. / 94 Read more »

'Anybody can be a white supremacist': The rise of white nationalist HispanicsThe diary of alleged gunman Mauricio Garcia sheds light on his hateful views.
Source: FOX26Houston - 🏆 448. / 53 Read more »

Dr. Saphier calls out 'disingenuous' White House for not giving Biden full cognitive testDr. Nicole Saphier joined 'Outnumbered' where she discussed concerns with Biden's medical acuity and urged the White House to release a cognitive evaluation.
Source: FoxNews - 🏆 9. / 87 Read more »

White House bans New York Post from attending Biden eventNew York Post correspondent Steven Nelson called out the White House for barring him from President Biden's event Monday, suggesting it's tied to the scandals plaguing his son Hunter.
Source: FoxNews - 🏆 9. / 87 Read more »