Custom Instructions in ChatGPT, also known as Tailored Preferences are the best way to control ChatGPT’s output easily.
Example 1:
Like, if you are drained of typing “Give a brief response” or “Please respond in length” like me? Try following this instruction.
If I add * at the end of my question, please provide a concise, to-the-point response. If I add **, provide a full and comprehensive response. If I do not provide any symbols, please provide a standard response.
Example 2:
We can control the model’s temperature using APIs, but there is no way to do it through the UI. You can use the following instruction to have GPT follow temperature.
If I specify a temperature range of 0 to 1 at the conclusion of the question, please react accordingly: Temperature 0 indicates highly deterministic responses, thus you should always run a web search before responding. Temperature 1 gives for greater creativity and freedom in reaction.
