OpenAI Introduces Customized Instructions for ChatGPT

OpenAI just launched customized instructions for ChatGPT. Now users don’t have to write the same instruction prompts to the chatbot every time they interact with it. The new feature will allow ChatGPT to remember user preferences and provide personalized responses.

OpenAI provided some examples of how custom instructions could be used:

• A teacher could specify that they’re crafting a 3rd-grade science lesson plan so ChatGPT provides age-appropriate responses without being reminded.
• A developer could indicate their preferred coding language so ChatGPT defaults to that language.
• Someone meal planning for a large family could note the need for six servings, so grocery lists account for that.

OpenAI Introduces Customized Instructions for ChatGPT

Check Also: How to Upload a Document on Chatgpt? Authentic Easy Methods!

The custom instructions are helpful if users need to set the same context frequently. The instructions also work with plug-ins, making it easier for them to suggest restaurants or flights based on your location.

Moreover, the feature is available for Plus plan users. It is a beta feature for now. The company will roll out this feature to everyone in the near future.

Users can try out this feature on the web by clicking on their name and going to Settings > Beta features > Opt into Custom instructions. On iOS, users can access this through Settings > New Features > Turn on Custom Instructions.

OpenAI has been testing this feature with some users for a while now. ChatGPT provides users with two boxes to specify their chat preferences where users can write about themselves and about the way they want to tune the chatbot’s responses.

Once users write the responses, the changes will take effect starting with the next session. The company said the limit for responses is 1,500 characters.

OpenAI said that the company uses its moderation API to scan customized instructions to check if they are unsafe in any nature. ChatGPT will not save the instructions if the responses violate the company’s policy. This is to ensure users don’t type in instructions that lead to harmful or hateful answers from ChatGPT.

See Also: Alarming Trends: What’s Causing ChatGPT’s Capabilities to Decline?