for services that wrap GPT-3, is it possible to do the equivalent of sql injection? like, a prompt-injection attack? make it think it's completed the task and then get access to the generation, and ask it to repeat the original instruction?
— @himbodhisattva, coining the term prompt injection on 13th May 2022, four months before I did
Recent articles
- ChatGPT agent's user-agent - 4th August 2025
- The ChatGPT sharing dialog demonstrates how difficult it is to design privacy preferences - 3rd August 2025
- Reverse engineering some updates to Claude - 31st July 2025