Skip to main content

ChatGPT is great, but it really needs these 4 new features

I know, it’s dumb to complain about a free service, which ChatGPT always has been. It feels especially silly for a technology that feels this new and exciting.

ChatGPT remains the best free AI chatbot out there — and yet, having used some of its rivals, coming back to ChatGPT can feel like a bare-bones experience. Here are five simple features that could really expand the usability of ChatGPT. Some of these would also make great additions to ChatGPT Plus, if the new features need to go there first.

A drafts option

Viewing different drafts in Google Bard.
Image used with permission by copyright holder

One of the neatest features of Google Bard is how it creates responses as drafts. It provides a single answer to your prompt, but then will also give you the option to see other versions or “drafts” of this same text. I’ve found this really useful. We all know that these AI chatbots always answer prompts in different ways, and being able to see variations on the response is so much more helpful than having to ask ChatGPT to “try that again.”

It’s commonplace in text-to-image generation to let the AI produce many, many options to choose from to home in on the desired image. I’d love to see a version of that for ChatGPT someday.

Continued conversations

It’s not talked about much, but ChatGPT does have a limit to how many chats can be in a conversation. It’s very large, but I know that I’ve run up against it before. I understand why ChatGPT needs to put limits on stuff like this, but it’s frustrating that there’s no way to continue the conversation in a new chat. This is especially true because of the way ChatGPT stacks chats into separate conversations rather than into one continuous stream.

ChatGPT seems to be able to learn from and use the context of responses and prompts in a single conversation to continue the train of thought. If there must be limits of conversations, it’d at least be nice to be able to continue the context of that conversation in a new chat.

Different modes and styles

The three conversation styles available in Bing Chat.
Image used with permission by copyright holder

The idea for this one is borrowed from Bing Chat. Microsoft’s own ChatGPT competitor is based on OpenAI’s technology, but offers some helpful ways of narrowing down the scope of a prompt. For example, Bing Chat let’s you choose from three different conversation styles: Creative, Balanced, and Precise. This tells Bing Chat how rigorous to be with knowledge and creativity. There’s also a “Compose” mode found in the Bing Chat Edge Copilot, which lets you choose from a number of different formats of writing and response lengths.

A lot of this can be achieved by using longer, more specific prompts that ask ChatGPT to respond in certain ways. But for beginners, these types of modes and limiters could make ChatGPT much easier to use. Having a slider for creative or precise modes could also adjust expectations about what kind of answers ChatGPT provides.

Suggested prompts

A screenshot of suggested prompts in Bing Chat.
Image used with permission by copyright holder

Suggested prompts are available in all sorts of different AI chatbots, most notably with Bing Chat. Like having different modes and styles, suggested follow-up prompts are really helpful for beginners who might not know how to continue the conversation with ChatGPT.

But even for more advanced users, I think suggested prompts could help expand your mind for what kinds of things ChatGPT can do to extend the conversation or get something closer to your desired result.

Voice prompts

There are ways to interact with ChatGPT using voice via plug-ins, but I’d love for OpenAI to incorporate voice as a standard feature. It would be great to be able to provide prompts over voice or receive answers read aloud. Obviously, if you’re using ChatGPT for coding, this would be silly, but having ChatGPT function a bit more like a voice assistant would be awesome in most other situations.

All the hardware capabilities currently exist in the devices using ChatGPT, so I’m not sure even how difficult this would be. It’d likely freak people out even more, but voice prompts could really help bring ChatGPT to life.

Editors' Recommendations

Luke Larsen
Senior Editor, Computing
Luke Larsen is the Senior editor of computing, managing all content covering laptops, monitors, PC hardware, Macs, and more.
New ‘poisoning’ tool spells trouble for AI text-to-image tech
Profile of head on computer chip artificial intelligence.

Professional artists and photographers annoyed at generative AI firms using their work to train their technology may soon have an effective way to respond that doesn't involve going to the courts.

Generative AI burst onto the scene with the launch of OpenAI’s ChatGPT chatbot almost a year ago. The tool is extremely adept at conversing in a very natural, human-like way, but to gain that ability it had to be trained on masses of data scraped from the web.

Read more
Apple may finally beef up Siri with AI smarts next year
The Siri activation animation on an iPhone running iOS 14.

As the world has been taken over by generative artificial intelligence (AI) tools like ChatGPT, Apple has stayed almost entirely out of the game. That could all change soon, though, as a new report claims the company is about to bring its own AI -- dubbed “Apple GPT” -- to a massive range of products and services.

That’s all according to reporter Mark Gurman, who has a strong track record when it comes to Apple leaks and rumors. In his latest Power On newsletter, Gurman alleges that “Apple executives were caught off guard by the industry’s sudden AI fever and have been scrambling since late last year to make up for lost time.”

Read more
OpenAI’s new tool can spot fake AI images, but there’s a catch
OpenAI Dall-E 3 alpha test version image.

Images generated by artificial intelligence (AI) have been causing plenty of consternation in recent months, with people understandably worried that they could be used to spread misinformation and deceive the public. Now, ChatGPT maker OpenAI is apparently working on a tool that can detect AI-generated images with 99% accuracy.

According to Bloomberg, OpenAI’s tool is designed to root out user-made pictures created by its own Dall-E 3 image generator. Speaking at the Wall Street Journal’s Tech Live event, Mira Murati, chief technology officer at OpenAI, claimed the tool is “99% reliable.” While the tech is being tested internally, there’s no release date yet.

Read more