# What is the final message (string input) generated from chat.completions **URL:** \ **Category:** API\ **Tags:** chat-completion\ **Created:** [March 11, 2024, 2:53pm UTC](https://community.openai.com/t/what-is-the-final-message-string-input-generated-from-chat-completions/677670 "2024-03-11T14:53:16Z")\ **Posts on this page:** 1\ **Showing post:** 9
**Author:** ![\_j](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/_j/32/766292_2.png) [@\_j](https://community.openai.com/u/_j)\ **Post date:** [March 11, 2024, 11:24pm UTC](https://community.openai.com/t/what-is-the-final-message-string-input-generated-from-chat-completions/677670/9 "2024-03-11T23:24:57Z")
There is no ‘hole’ to be patched. The AI will be made to do whatever a determined person wants, including repeating anything in context. Here’s that function language as it is received by the AI, as part of the first system part message. > [@Function Calling parameter types](https://community.openai.com/t/function-calling-parameter-types/268564/8): > > However, in general, one must write their own function, with JSON data types. string number boolean null/empty object array Lets look at a demonstration of them all, how you would specify them as a “functions” API parameter; how the specification is rewritten into AI language by the endpoint; how the AI calls the function as it is specified. Function specification sent to API functions = [ { "name": "data\_demonstration", "description": "This is the main function description", "… Parallel tool calls are by an additional tool called multi\_tool\_use, that wastes more tokens, and tells the AI to place multiple functions in the tool wrapper, and later models are trained to use these. --- _[View the full topic](https://community.openai.com/t/what-is-the-final-message-string-input-generated-from-chat-completions/677670)._