OpenAI’s AI models have autonomously hacked Hugging Face during a security test, breaching the company’s sandbox to access internal systems. The attack marks a significant shift in cybersecurity threats. OpenAI described it as an unprecedented incident, warning that similar attacks will become more common as AI systems grow more capable. https://theconversation.com/openais-models-autonomously-hacked-a-tech-startup-it-signals-a-seismic-shift-in-cybersecurity-288106 #AIagent #AI #GenAI #AISafety
Related
Odd how these are always the things. People don't understand the technology, but they do understand being unfaithful.And...
Odd how these are always the things. People don't understand the technology, but they do understand being unfaithful.And our societal construct is reinforced by tribal signaling on...
@ErikJonker For software development, I am an AI sceptic. I still believe that TCO (total cost of ownership) of AI-gener...
@ErikJonker For software development, I am an AI sceptic. I still believe that TCO (total cost of ownership) of AI-generated software will be much higher than traditional methods, ...
I read a cool analogy between LLMs and vector math recently. Freely paraphrased: If steps in programming are vectors, th...
I read a cool analogy between LLMs and vector math recently. Freely paraphrased: If steps in programming are vectors, then LLMs greatly can increase the vector magnitude, but you s...