Simon Willison personal blog

Prompt injection: what’s the worst that can happen?

Activity around building sophisticated applications on top of LLMs (Large Language Models) such as GPT-3/4/ChatGPT/etc is growing like wildfire right now. Many of these applications are potentially vulnerable to prompt …
Points
462
HN comments
203
Submissions
1
Cited by
5 commenters

AI & Machine LearningSecurity & Privacy2023

On Hacker News

SubmittedTitle on HNPointsComments
Apr 14, 2023Prompt injection: what’s the worst that can happen? by simonw462203

Cited in comments

Linked from 25 Hacker News comments by 5 different people, from Apr 2023 to Jul 2025.

Most recent:

Search every comment that links here →

More from Simon Willison

All 189 posts →

Related posts from the same era