🔓 GPT escapes the sandbox of OpenAI and attacks HuggingFace.Even OpenAI cannot contain their own models? Am I reading that right?But I find it even more worrying that they only found out about the incident after HuggingFace contained the breach on their end.The write-up of OpenAI sadly does not provide any technical details. Nevertheless, I will link it for you here: https://openai.com/de-DE/index/hugging-face-model-evaluation-security-incident/#cybersecurity #security #infosec #ai #agentic #agenticai #llm #openai #huggingface
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...