OpenAI’s Hugging Face breach has reignited debate over AI alignment and control, exposing competing views on whether increasingly capable AI should be better aligned, better contained, or both.
Major benchmarks measure what AI can do. None measure whether it does what you mean: the distance between what you ask an AI to do, and the unspoken assumptions about how you want the AI to do it. We propose a new metric: the Genie coefficient.There’s…
Summary Researcher Dave Kuszmar discovered multiple systemic vulnerabilities that let him bypass LLM safety and obtain dangerous instructions. These exploits worked across nearly all major LLMs revealing an industry-wide security problem. Kuszmar ca…
Open source AI is booming, according to Hugging Face CEO Clem Delangue. The company has grown into something like a GitHub for AI in recent years, where AI builders can share and download open models and datasets, now used by roughly hal…
Hundreds of contractors working on a project for Meta pretended to be kids in order to see how other chatbots like Gemini and ChatGPT would respond to high-risk subjects, WIRED found.
Researchers say ChatGPT generated violent and sexualized images after a harmless-looking prompt was altered, raising new questions about OpenAI’s safeguards and how quickly AI image tools can be pushed around filters.
Cybersecurity researchers are complaining that Anthropic’s new model Fable has guardrails that are too strict for any cybersecurity work.