Skip to main content
  1. Home
  2. Computing
  3. News

This new ChatGPT feature could greatly expand usability

By

ChatGPT is a simple, straightforward application. It’s an empty box to type into, and not much more.

But according to AI enthusiast Rowan Cheung, some ChatGPT Plus users have reported that a new feature is being tested and will be rolled out that will add some ways of narrowing down your prompts to get a response that’s a bit more targeted.

Recommended Videos

🚨Breaking:

Some ChatGPT users are reporting a new mini toggle helper.

This will allow users to prompt ChatGPT much faster, and could be the start of prompt templates 👀
pic.twitter.com/rihWF3FyMA

— Rowan Cheung (@rowancheung) March 29, 2023

Related

In the video posted by Cheung, you can see a drop-down menu with simple actions as ways of tweaking the results provided. You can clarify, exemplify, expand, explain, rewrite, or shorten. It’s not hard to see how this kind of a menu would allow you to pinpoint the exact kind of result you’re aiming for.

These kinds of tools are features we’ve seen Microsoft experiment with on its Bing Chat tool, which is also built on OpenAI’s large language models. You can select from different tones, formats, and lengths — as well as choose between its Chat, Compose, and Insights panels. Even beyond those options, Bing Chat gives you the broader choice of Creative, Balanced, and Precise modes, which make them easier tools for a beginner to use. Microsoft has a similar way of tweaking responses built into its Bing Image Creator and other Microsoft Office Copilot implementations.

However, these types of menus and options can also start to feel like they limit the creativity of the user. Being able to ask the AI to do anything is what makes it quite so powerful.

There’s been no indication so far if the new drop-down menus are going to be a permanent feature of ChatGPT Plus — or if it’s just something OpenAI is currently testing.

Editors' Recommendations

Topics
Luke Larsen
Luke Larsen
Senior Editor, Computing
Luke Larsen is the Senior editor of computing, managing all content covering laptops, monitors, PC hardware, Macs, and more.
Why Meta’s new ChatGPT rival is such a big deal
Meta and Microsoft's Llama 2 is an AI model that is supposed to be as good a ChatGPT.

ChatGPT has enjoyed a huge advantage over its competitors, even companies as large as Google. But Meta has recently announced the latest iteration of its AI model, Llama 2 (Large Language Model Meta), along with the open availability of the model for free to developers for research and commercial purposes.

For the first time this year, we may be witnessing the most significant challenge so far to OpenAI's grip on the world of generative AI.
It's open source

Read more
Here’s why people think GPT-4 might be getting dumber over time
A laptop screen shows the home page for ChatGPT, OpenAI's artificial intelligence chatbot.

As impressive as GPT-4 was at launch, some onlookers have observed that has lost some of its accuracy and power. These observations have been posted online for months now, including on the OpenAI forums.

These feelings have been out there for a while, but now we may finally have proof. A study conducted in collaboration with Stanford University and UC Berkeley suggests that GPT-4 has not improved its response proficiency but has in fact gotten worse with further updates to the language model.

Read more
Top authors demand payment from AI firms for using their work
Person typing on a MacBook.

More than 9,000 authors have signed an open letter to leading tech firms expressing concern over how they're using their copyrighted work to train AI-powered chatbots.

Sent by the Authors Guild to CEOs of OpenAI, Alphabet, Meta, Stability AI, IBM, and Microsoft, the letter calls attention to what it describes as “the inherent injustice in exploiting our works as part of your AI systems without our consent, credit, or compensation.”

Read more