Open AI’s Astra model is on the way — and very good at breaking into computer systems

OpenAI previewed the safeguards it is putting in place ahead of the launch of Astra, its newest cyber‑critical large language model. The model is described as being particularly adept at penetrating computer systems. The company says it is implementing precautions to mitigate misuse.

Summary written by Kernelia from the original article by TechCrunch AI. The story and its rights belong to its author.