Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Multi-modal prompt injection image attacks against GPT-4V. Parent comment
The exfiltration demo in the blog post doesn't show ChatGPT fetching a URL: it shows it outputting an image tag with an src= pointing at an external URL, which the user's browser then attempts to load.
There are no comments on this comment yet.
The exfiltration demo in the blog post doesn't show ChatGPT fetching a URL: it shows it outputting an image tag with an src= pointing at an external URL, which the user's browser then attempts to load.