AI & machine learning2022 · shared on Hacker News
Susceptibility of Pre-Trained Language Models to Handcrafted Command Injection
Explore Susceptibility of Pre-Trained Language Models to Handcrafted Command Injection, its original source and Hacker News discussions. Discover community perspectives and save it to your reading list.
GO BEYOND THE ABSTRACT
The conversation around the idea.
Original Hacker News threads. Different perspectives, questions, and things worth thinking about.
Showing up to 100 related threads. A paper may appear in a comment rather than the original submission.
Links found in the discussion
Up to 50 recent source links, in HN item order.
Ysimonw ·
Prompt injection attacks against GPT-3
208 points113 comments
Yupwardbound ·
Susceptibility of Pre-Trained Language Models to Handcrafted Command Injection
2 points0 comments