Simon Willison personal blog
Prompt injection attacks against GPT-3
Riley Goodside, yesterday: Exploiting GPT-3 prompts with malicious inputs that order the model to ignore its previous directions. pic.twitter.com/I0NVr9LOJq- Riley Goodside (@goodside) September 12, 2022 Riley provided several examples. Here’s …
- Points
- 208
- HN comments
- 113
- Submissions
- 1
- Cited by
- 5 commenters
AI & Machine LearningSecurity & Privacy2022
On Hacker News
| Submitted | Title on HN | Points | Comments |
|---|---|---|---|
| Sep 12, 2022 | Prompt injection attacks against GPT-3 by simonw | 208 | 113 |
Cited in comments
Linked from 12 Hacker News comments by 5 different people, from Oct 2022 to Jan 2026.
Most recent:
