The most recent OpenAI updates may have flown under the radar for some, but trying them firsthand is mind-blowing.

 

“OpenAI Updates Made ChatGPT and Dalle-3 Stronger Than Ever”


 

In the storm of AI tools, you might have already bumped into several articles and social media posts claiming that “ChatGPT is dead”, but unsurprisingly, they think it very differently. Since first propelling Dall-E and ChatGPT (both by OpenAI) into the spotlight, several events have unfolded in the Generative AI industry, with giants making their entrance. But apparently, they are not relinquishing their leading role just yet.

Starting with ChatGPT, in the last few months, newer and newer plugins popped up every day,  but especially in real-time browsing we’ve experienced disappointment due to error messages and inconsistent functionality from third-party AI tools. But recently this changed as OpenAI integrated a browsing option with Bing (for Plus users only). The provided results always have to be handled carefully and need to be researched, but this update already outperforms previous plugins. Notably, it uses references.

What better way to illustrate this than asking ChatGPT through Bing about OpenAI’s most recent updates?

ChatGPT Updates:

(by ChatGPT on 14.10.2023)


Thank you for reading this post, don't forget to subscribe to our AI NAVIGATOR!


 

Browse Feature (September 27, 2023):

  • ChatGPT can now browse the internet to provide current and authoritative information with direct links to sources. This feature is available to all Plus users and is no longer limited to data before September 2021​1​.

Voice and Image Capabilities (September 25, 2023):

  • Voice (Beta) is now available to Plus users on iOS and Android, allowing back-and-forth voice conversations.
  • Image input is available to Plus users on all platforms. Users can now show ChatGPT images to troubleshoot issues, explore contents, or analyze complex graphs​2​.

Language Support (September 11, 2023):

  • Alpha support for multiple languages including Chinese, French, German, Italian, Japanese, Portuguese, Russian, and Spanish on web​2​.

ChatGPT Enterprise (August 28, 2023):

  • Launch of ChatGPT Enterprise offering enterprise-grade security, privacy, unlimited higher-speed GPT-4 access, longer context windows for processing longer inputs, advanced data analysis capabilities, and customization options​2​.

Custom Instructions (August 2023):

  • Custom instructions are now available to users in the EU, UK and to free users allowing them to customize interactions with ChatGPT​2​.

Voice and Image Analysis Capabilities:

  • The update also introduced voice and image analysis capabilities, making the interaction more intuitive​3​.

Being able to—and doing so—check the references is immensely helpful, and in this instance, it directs us to reliable pages, including OpenAI’s own Release Notes.

Quite useful results, through which you can also find the Open AI announcement published on 25 September, where you’ll find a detailed guide on how to use the new image and voice feature.

The chatbot also provided us with the news about Dall-E:

DALL-E Updates:

(by ChatGPT on 14.10.2023)

DALL-E 3 Launch (September 2023):

  • DALL-E 3 was announced with enhanced capabilities for understanding “significantly more nuance and detail” compared to previous iterations​4​.

Safety Measures:

  • DALL-E 3 continues the focus on safety by limiting the ability to generate violent, adult, or hateful content​5​.

Integration with Bing Image Creator:

  • DALL-E 3 was integrated into Bing Image Creator, facilitating the creation of realistic images and a wide range of artwork by following simple prompts​6​​7​.

Those with a keen eye may have already spotted the available integration with Dall-E 3, simplifying user experiences remarkably. Outweighing even this is Dall-E 3’s improved model and its ability to craft detailed images with mostly accurate spelling.

Here is an example of using Dall-E 3 inside ChatGPT.

Although it still contains mistakes, it is much improved from the previous model, making creative work significantly faster.

The quality of the human faces is much better, and the dreaded hand-sketching barrier has been eliminated.

The combination of creating these visuals just a click away from using GPT-4’s model for creating uncountable complex texts, codes and real-time searches makes it an even more valuable tool than it had ever been before.

Now, we only mentioned a few of OpenAI’s updates, but starting with the Custom Instructions, through documents readability, the supposed API updates, to Canva’s integration, there are several other exciting pieces of news to explore in more depth.

If you liked this article and would be interested in reading more like this, let us know!