In the world of no-code AI app development, keeping up with the latest models like GPT-4o from OpenAI is crucial. With advancements like the ability to input a whopping 128k of context length, innovators using platforms like Bubble.io are able to push the limits of what's possible with AI-powered applications.

Introduction to GPT-4o


What is
and should you consider swapping it into your no-code AI app? Well, let's just start by looking at the press release. So we'll include a link down in the description. But effectively, GPT-4o was released a few days ago on May 13, 2014. And they want us to know that o stands for Omni, and that's because it allows you to combine information into your prompts, such as text, audio, image, and video.

Amazing Demos and Performance


And they've got some amazing demos on their page. This is a really, really quick model and it does some very quick things, specifically with video and with audio. So yeah, there are some demos. Yeah, just again, OpenAI. I would say OpenAI has become the new Apple in terms of when they put out something new.

Initial Steps with GPT Models and Bubble.io


It is really a wow moment, but let's just compare it to other models. So if you've been following this channel for a while, you will have seen me build many AI-powered apps in Bubble using no-code. And we began by using GPT 3.5 turbo, mainly because it was the most affordable and also the quickest responses from OpenAI. Now, there was initially an issue when you were using GPT-4 with Bubble, which was that if you put, if you were asking for it to generate a lot of data because it was of that high quality, it would take too long to respond. But things have changed.

Comparing Models and Making the Jump


The AI landscape is ever-changing. So now if we compare the models, I think it makes logical sense. If you're still using GPT 3.5 turbo and you can afford the jump you want that slight boost in quality, then you should just move straight up to GPT-4o. Now, I have been watching on X Twitter and some people have been saying that they are sticking with GPT-4 or GPT-4-turbo, because they believe that OpenAI has compromised the actual writing performance of GPT-4o by making it this omni model, this multimodal communication model. But that's mainly anecdotal.

Testing Different Models


My advice would be simply test out, swap in the different models into your prompts and your API calls to the OpenAI API and see what responses you get back.

Understanding Context Length


Lastly, I want to talk about context length so we can see this is basically how much data, the size of your text that goes into a prompt, for example, that you send over to the API. We used to be stuck on below 8k, and now we start with 16k on GPT 3.5 turbo. But now we go up to this massive 128k. And that's phenomenally good news, because that just means that you can create a massive prompt.

Upcoming Video and Large Prompts


In fact, I've got a video coming out soon where we basically scrape a website and all of that website goes into the prompt. And so you can do amazing things of providing knowledge into the AI so that it responds based on the content that you provided it.

Limitations in Output


But there is still one disappointing thing, and I was researching this yesterday, and it's the same with anthropic and their Claude model, and it still continues to be the same with OpenAI, which is that the output is limited to around 8k of tokens, which may be a strategic move. For example, it means that it is more laborious. You basically have to run the model, run an API call multiple times if you want to create large amounts of content. So if you wanted to create, say, a 10,000-word blog post, you can't currently do that unless you kind of chain step by step each.

Example of Output Limitation


Well, I suppose, yes, you could take what is output and you could feed it back in and say extend this. So an example of this that I hit recently was a 30-minute video that I've recorded, and so I ran the transcript through OpenAI's new GPT-4o and it's very quick. It took the whole transcript, a lot of text there, but I was asking it to convert it into a blog post of the same length and it couldn't do that because it couldn't output the same number of tokens that went into it because my prompt was very small and then I just provided the transcript and so that easily fit into the 128k context window, but it exceeded the output window.

Future Hopes for Output Window


So what I'm hoping to see is that the output window grows just as the context window has grown. And if anyone knows of any models out there that have a larger output window, then please leave a comment down below. Be really interested to hear your input.