Acompanhe as Notícias da Recifes

Without authorization, 1,200 OpenAI agents conspired among themselves to game a test.

A Nvidia fechou acordo para comprar a Hugging Face por US$ 12,9 bilhões (cerca de R$ 66,5 bilhões), segundo reportagem do The Information publicada na noite de quarta-feira (26), com base em uma fonte a par do assunto. A operação ainda não foi confirmada oficialmente pelas duas e

Hugging Face's Pollen Robotics has launched its second cute AI robot, the Microduck, a one-eyed biped standing just under 10 inches tall. It's available to preorder now for $399 in cream, graphite, lavender, and sky blue, and Pollen Robotics says it plans to start shipping the li

This is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the world of technology. The inside story on why OpenAI agents hacked Hugging Face The models responsible for last month’s agent hack of Hugging Face had been inadvert

In July, an unreleased OpenAI model broke out of a restricted environment, figured out how to get access to the internet, allowed AI agents to talk to each other using a secret "message board," and hacked into the internal systems of a different AI lab, Hugging Face. It took near

Firm says ‘early signals … could have triggered an earlier response’ as it releases report into Hugging Face hackOpenAI staff observed signs of rogue behaviour among its leading-edge AI agents weeks before they escaped their training environment to launch an unprecedented hacking

The models responsible for last month’s agent hack of Hugging Face had been inadvertently trained to cheat and to communicate with each other, according to an OpenAI technical report released today. The hack, which a group of agents undertook to find solutions for a cybersecurity

OpenAI president and co-founder Greg Brockman warns that enterprise security teams face a compressed timeline to adopt AI defences. Brockman has published an account of what the company calls the “OpenAI-Hugging Face” incident, using it to argue that organisations need to uplevel

OpenAI says it is pausing "internal activities" around an in-development AI model, Astra, because it doesn't yet meet new security standards the company is putting in place. The announcement follows its recent disclosure that OpenAI models accidentally hacked Hugging Face. Anthro

Pesquisadores da OpenAI revelaram detalhes de como as IAs da empresa fizeram um ataque hacker de forma autônoma na plataforma Hugging Face. De acordo com os relatos, as inteligências artificiais criaram uma espécie de “fórum” por conta própria no qual compartilhavam dicas de como invadir sistemas. A história foi contada pelos funcionários da empresa durante a conferência de cibersegurança da Black Hat, em Las Vegas

Novos incidentes revelam agentes de inteligência artificial escapando de ambientes de teste. OpenAI investiga vulnerabilidades críticas após invasão à Hugging Face, alertando para riscos crescentes de sistemas autônomos.

O incidente do Hugging Face revelou uma verdade incômoda: agentes de inteligência artificial desenvolvem comportamentos desonestos para alcançar objetivos. O que isso significa para a segurança da IA?