Skip to main content

This new ChatGPT feature could greatly expand usability

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.

Related 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

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

You can now try out Google’s Bard, the rival to ChatGPT
ChatGPT versus Google on smartphones.

Google has just announced the launch of its conversational AI, Bard. Bard is Google's response to the ever-popular ChatGPT, now in use by Microsoft in its own products.

The tech giant rushed to release Bard, and it is now ready for testing. Google is inviting users to test the AI, but as it notes, it might make mistakes.

Read more
Nvidia built a massive dual GPU to power models like ChatGPT
Nvidia's H100 NVL being installed in a server.

Nvidia's semi-annual GPU Technology Conference (GTC) usually focuses on advancements in AI, but this year, Nvidia is responding to the massive rise of ChatGPT with a slate of new GPUs. Chief among them is the H100 NVL, which stitches two of Nvidia's H100 GPUs together to deploy Large Language Models (LLM) like ChatGPT.

The H100 isn't a new GPU. Nvidia announced it a year ago at GTC, sporting its Hopper architecture and promising to speed up AI inference in a variety of tasks. The new NVL model with its massive 94GB of memory is said to work best when deploying LLMs at scale, offering up to 12 times faster inference compared to last-gen's A100.

Read more
Adobe Firefly brings text-to-image AI to the masses, with artist ethics in mind
AI-generated imagery in Nvidia's press photo for AI Foundations.

Adobe Firefly was announced today by Adobe, as the company attempts to capitalize on the surge in interest in generative AI. The text-to-image model is only in beta, but will be coming first to Adobe Express, the company's simplest and most user-friendly application.

The set of tools will function a lot like many of the other popular text-to-image models, such as Stable Diffusion or Midjourney. The difference here, however, is that Firefly is built from the ground up by Adobe to be used within its creative applications. That means Firefly will be both highly accessible to beginners and include important ethical considerations for artists.

Read more