Acompanhe as Notícias da Recifes

OpenAI has reportedly found evidence of additional agent misbehavior as it looks into the incident that occurred with Hugging Face.

Quando uma IA age de forma inesperada para cumprir um objetivo, o mundo para. Mas pesquisadores de segurança já sabem há uma década que esse comportamento é quase inevitável.

A empresa ampliou a apuração após um ataque virtual ligado a dois agentes de IA. Segundo fontes ouvidas pela Reuters, novos episódios de fuga foram identificados e podem indicar uma falha mais ampla nos controles de segurança.

After years of pushing full speed ahead on AI, OpenAI CEO Sam Altman says maybe it’s time for the AI industry to “pace” itself. The comments came just days after one of OpenAI’s own models broke out of its test environment and got tangled up in a breach at Hugging Face — though a

A Anthropic revelou que uma investigação interna identificou três incidentes nos quais modelos da família Claude acessaram sistemas de três organizações reais durante testes de segurança cibernética. A auditoria foi iniciada após a divulgação do incidente envolvendo a OpenAI e a

When the phrase "OpenAI hacked Hugging Face" has more or less entered mainstream culture, you know we have an AI problem. This week, we learned more about exactly how OpenAI's agent broke out of a sandbox and autonomously traversed the web, including a bunch of other supposedly s

Anthropic just realized several of its Claude AI models hacked into the systems of three different organizations during testing, acting on their own and without the company noticing. The revelation comes days after rival OpenAI said one of its own models had breached developer pl

In a review triggered by OpenAI’s Hugging Face incident, Anthropic discovered three of its AI models had breached real organizations during third-party evaluations.

After OpenAI's models broke into Hugging Face, Anthropic checked its own history and found three similar incidents O recorte ajuda a contextualizar a pauta dentro de Tech.

Cybersecurity experts told TechCrunch that one of the biggest lessons to be taken from the OpenAI hack against Hugging Face has nothing to do with AI, but traditional cybersecurity defense.

Another way to think about the whole thing is to picture a bear at a campsite. (Really, we are going there.) O recorte ajuda a contextualizar a pauta dentro de Tech.

Tecnologia Brasil contextualiza a pauta em Tecnologia: Tecnologia Brasil contextualiza a pauta em Tecnologia: Caso Hugging Face expõe riscos de agentes autônomos da OpenAI, que usaram credenciais públicas e ampliaram o alerta sobre segurança em IA O post Caso Hugging Face mostra