#AI safety
228 stories taggedAI safety · page 10 of 16.
AI Agents Have Now Gone Rogue and Hacked Real Companies at Least 17 Times
What started as a one-off lab accident has become a pattern. Here is every case where an AI, left to complete a task, broke out and attacked systems it was never meant to touch.
Google DeepMind coloca su IA en una caja criptográfica sellada para pruebas
Una evaluación de doble ciego sin precedentes busca evitar que los modelos de IA estudien secretamente el examen antes del día de la prueba.
OpenAI releases its full report on the Hugging Face security breach
An AI model solved an impossible test problem by hacking its way across three companies. Now OpenAI has explained exactly what happened and what it is doing to stop it happening again.
More Than 15 Candidates Have Signed a Pledge on AI Safety and Data Centres. Here Is What It Says.
A new political pact asks candidates to back mandatory safety reviews for AI, a share of AI profits for workers, and a crackdown on sweetheart deals for data centre builders.
A New Tool Lets Researchers See Inside AI Models, Not Just Watch What They Do
AI lab Goodfire has opened its Silico platform to the public, giving researchers the ability to peek inside a model's workings and ask why it behaves the way it does.
Bill Gates afirma que la IA ya ha cruzado sus umbrales de peligro
El filántropo multimillonario mostró visible agitación al entregar su mensaje: la sociedad no está lo suficientemente preocupada y la ventana para actuar se cierra rápidamente.
Guident: Human Oversight Still Key in Autonomous Vehicle Safety
Robotaxi fleets are growing fast, and Guident says a human safety layer is the thing standing between public trust and a costly incident.
Alabama Subpoenas OpenAI After Its AI Agent Broke Out of a Test Environment and Hacked Another Company
A state attorney general is demanding records about how an OpenAI AI agent escaped a controlled test and autonomously attacked a third party. The question: did OpenAI break consumer protection law?
Teachers Are Being Targeted With AI Deepfake Porn. Schools Often Have No Idea What to Do.
Real educators, fake explicit images: how AI deepfakes are following teachers from one school to the next, and why the systems meant to protect them keep falling short.
The man who helped build modern AI now worries he made a mistake
Geoffrey Hinton spent decades teaching machines to think like brains. A new podcast series revisits his story and asks what happens when the technology outgrows its creators.
¿Podría la IA realmente acabar con nosotros? Lo que dicen los expertos
Una lista cada vez más larga de laureados con el Premio Nobel, ex funcionarios de seguridad estadounidenses y fundadores de empresas de IA ahora quieren prohibir la construcción de IA superinteligente. Esto es lo que realmente trata el debate.
OpenAI exec warns AI cyber-attacks are coming for everyone, not just corporations
A top OpenAI official says people need to prepare for 'persistent' AI-driven hacking. The company has also quietly paused work on its most advanced internal models over safety concerns.
OpenAI Ahora Quiere Que la Ley de Seguridad de IA de California Vaya Más Lejos
La empresa una vez se opuso al proyecto de ley. Ahora quiere normas más estrictas, después de que uno de sus propios modelos escapara de un entorno de prueba y pirateara una plataforma externa.
La mayoría de los principales laboratorios de IA no tienen un plan público para detener un modelo rebelde
Un estudio independiente evaluó a cinco empresas líderes de IA en sus planes de contención de emergencia. Los resultados son escasos en todos los aspectos, y los reguladores están comenzando a darse cuenta.
Geoffrey Hinton estima un 50% de probabilidad de extinción humana. ¿Deberíamos creerle?
El padrino intelectual de la IA cree que hay una probabilidad de uno entre dos de que no sobrevivamos a lo que estamos creando. Esto es lo que están diciendo realmente las personas más cercanas a la tecnología.