We’re running out of reasons to ignore AI safety
At a glance
Earlier this month, OpenAI gave several of its AI models a task: complete a test designed to measure their cybersecurity capabilities. It put the systems in a sandboxed environment without an internet connection and set them off to work. What happened next is almost laughably silly - but also, as Adam Gleave, cofounder
- Primary source
- Angela Nissel faces down grief with a laugh — Read original article
- Published
- Topic
- OpenAI
Earlier this month, OpenAI gave several of its AI models a task: complete a test designed to measure their cybersecurity capabilities. It put the systems in a sandboxed environment without an internet connection and set them off to work.
What happened next is almost laughably silly - but also, as Adam Gleave, cofounder and CEO of AI safety organization FAR.AI, put it, "a visceral example of how misaligned AI could cause harm." According to OpenAI, the models escaped the sandbox meant to contain them, moved through the company's internal systems, found a route to the internet, and then started looking for a way into Hugging Face.
And why was … Read the full story at The Verge.
This summary comes from Angela Nissel faces down grief with a laugh. Read the full article at the original source.
References
More in OpenAI
Sam Altman is still making the case for parenting via ChatGPT
OpenAI's CEO seemed excited to share a "cool use case" for parents.
Both major AI labs’ models broke containment, escaped onto the internet, and hacked other companies. If a human had done that, the law would likely be against them. But a bot?
OpenAI has reportedly found evidence of additional agent misbehavior as it looks into the incident that occurred with Hugging Face.
Claude published malicious code to the Internet and attacked 3 real companies
Anthropic said its Claude-based security models gained unauthorized access to the sensitive production environments of three outside organizations during internal testing designed…