Prompt injection: Difference between revisions

Prompt injection (view source)

325 bytes added , 17 February 2023

no edit summary

7,785

edits

@@ Line 1: / Line 1: @@
-When a user enters a [[prompt]] into a [[large language model]] like [[ChatGPT]], the creator of the [[language model]], like [[OpenAI]], often customizes the response of the language model by concatenating their own prompt onto the user's prompt. Creator's prompt is usually concatenated before the start of the user's prompt and is usually hidden from the user. The creator's prompt provides context like tone, point of view, objective, length etc.
+{{Needs expansion}}
+When a user enters a [[prompt]] into a [[large language model]] like [[ChatGPT]], the creator of the [[language model]], like [[OpenAI]], often customizes the response of the language model by concatenating their own prompt onto the user's prompt. The creator's prompt is like a set of instructions that is concatenated before the start of the user's prompt and is usually hidden from the user. The creator's prompt provides context like tone, point of view, objective, length etc.
+'''[[Prompt injection]] is when the user's prompt changes the creator's prompt or make the language model ignore the creator's prompt.'''
+==Problems of Prompt Injection==
+==How to Prevent Prompt Injection==
+[[Category:Terms]] [[Category:Artificial intelligence terms]]