I don’t know how well this has been published worldwide yet. Meanwhile, an article in The Times today was published that Microsoft (they have a rather large chunk of investment in ChatGPT) is planning to release a significant upgrade:

“A new version of the artificial intelligence that powers ChatGPT will be released this week that can turn text into video and other media, according to a Microsoft executive.”

“GPT-4 is a more powerful and versatile update of GPT3.5, the large language model that sits behind ChatGPT, which has caused a sensation because of its ability to write well in many formats based on text commands. More than 100 million people use it regularly since it was launched at the end of November, making it the fastest growing application in technology history.”

“Now the world needs to prepare for another step change after Andreas Braun, chief technology officer for Microsoft in Germany, said on Friday: “We will introduce GPT-4 next week, there we will have multimodal models that will offer completely different possibilities – for example videos.” The event was reported by the German publication Heise.” Source: https://www.thetimes.co.uk/art…

The article also shares some concerns (it wouldn’t be journalism if it didn’t) about the fast evolution of generative AI, but I only care about its upside. OpenAI was approached for comment, but nothing yet.

After I read it, I asked ChatGPT about it:

Me: “What can you tell me about the new version of the artificial intelligence that powers ChatGPT that will be released this week that can turn text into video and other media, according to a Microsoft executive.”

ChatGPT: “As an AI language model, I can confirm that Microsoft has been working on a new version of its AI technology that reportedly has the ability to transform text into various forms of media, including video. The technology is called DALL-E 2, and it builds upon the company’s previous work on GPT-3, which I am currently based on.

According to reports, DALL-E 2 uses a combination of natural language processing and computer vision to create visual content based on textual prompts. This could potentially revolutionize the way we communicate and create content, as it would enable people to easily generate visual media without needing specialized skills or software.

It is worth noting, however, that as an AI language model, I do not have direct access to the specifics of Microsoft’s technology or the details of the release. It is always important to evaluate new technologies with a critical eye and consider the potential implications and limitations.”

So, that.