ChatGPT Now Has Customized Instructions From OpenAI

(CTN News) – ChatGPT has just launched custom instructions for ChatGPT users so they don’t have to write the same instructions to the chatbot every time they interact with it.

Inputs such as “Write the answer in under 1,000 words” or “Keep the tone formal” can be recorded.

According to the company, this feature allows you to inform ChatGPT of anything you would like it to consider when responding.

For instance, when asking for suggestions, a teacher can mention that they are teaching fourth-grade math or a developer can specify the programming language they prefer.

Additionally, ChatGPT can be configured to provide responses based on the size of your family, so you can plan meals, grocery shopping, and vacations accordingly.

Despite the fact that users can already specify these things while chatting with the bot, custom instructions may be helpful if they need to set the same context on a regular basis.

It also works with plug-ins, making it easier for them to suggest restaurants or flights based on your location.

Users of OpenAI’s Plus plan have access to the feature, however users residing in the EU and the U.K. will not have access to it. Currently, it is a beta feature.

To try out this feature, users should click on their name and select Settings > Beta features > Opt into Custom instructions. Users can access this feature on iOS by going to Settings > New Features > Turn on Custom Instructions.

It should be noted that OpenAI states that the information given to customized responses will be used to train its API models to adapt to different instructions.

In addition to improving model performance, information from custom instructions will be used to teach the model how to adjust its responses to your instructions without exceeding them, the company stated. Nevertheless, users may opt out of this setting by adjusting their data control settings.

It has been a while since OpenAI has tested this feature with some users, as noted on Twitter by consultant Gavriel Cohen.

Users can customize the chatbot’s responses using two boxes in the ChatGPT application.

As soon as users key in their responses, the changes will be reflected in the following session. There is a limit of 1,500 characters for responses, according to the company.

A spokesperson for OpenAI said that the company uses its moderation API to scan customized instructions for any signs of unsafe behavior.

If the instructions result in responses that violate the company’s policies, ChatGPT can refuse to save them or ignore them. ChatGPT ensures that users do not type in instructions that will result in harmful or hateful responses.

OpenAI launched ChatGPT for iOS in May exclusively for U.S.-based users. In the weeks following that announcement, the company expanded its availability to more than 40 countries.

The startup launched an iPad app last month that supports Siri and Shortcuts. From the ChatGPT app, users can also search the web for answers through Bing.

SEE ALSO:

WhatsApp Is Redesigning Its Security Notifications Menu

Microsoft Expands Cloud Logging to Counter Rising Nation-State Cyber Threats