Hacker News Reader

It baffles me that the interface into the ChatGPT API is a blob of unstructured text. This seems to be the core reason for this attack vector.

Why is there no structured API into ChatGPT? I developed some tools with the Amazon Alexa voice API about a decade ago and remember that was the default operating mode. There were different classes for weather, tasks, Q&A, etc. Never heard of a "prompt injection" attack against the Alexa API...

View on HN

There is/was something close to prompt injection with Alexa and other smart speakers - https://www.theregister.com/2022/03/03/amazon_alexa_speaker_...

There is a distinction in the ChatGPT chat completion API between "system" text and "user" text, but GPT 3 had a problem where it would basically ignore any system text, so you had to put instructions in the user text anyway. Not sure if it's changed for GPT 4.

Reply on news.ycombinator.com