Limited Time Offer: Watch All Our Bubble Tutorial Videos for Only $99 per Year!

Is Claude 3 better than OpenAI GPT-4?

Discover the power of Anthropic's Claude 3 models for building AI integrated no-code apps using Bubble.io. Explore how the latest AI models like Claude 3 Haiku can outperform even GPT 4, revolutionizing the landscape of app development.

Introduction

I coach and tutor many Bubble app builders each week, and a lot of them are making really exciting AI powered apps. And most of them, in actual fact, all of them that I've worked with so far, are using OpenAI's API to power their apps. They're tapping into the same power that powers chat, GPT, and they're using mainly GPT 3.5 turbo and GPT-4.

Exciting News

Well, we've got a little bit of exciting news today, and if you are using OpenAI, then take this as your encouragement to try out three. Because based on this table, where they claim they've collected over 400,000 human preferences, basically, people get to vote on the output of different AI models and it's all gone through statistical algorithm and we get a table like this, and at the top, what do we see?

Introduction to Claude 3 Opus

We see Claude three Opus. As a reminder, if we go back to Claude's press release, we can see that Opus is their most expensive and yet also their most powerful model. In terms of pricing, there's a slight difference, but think of it like GPT four. But here's where it gets interesting. As you scroll down, you can see, right, so we go past some GPT four previews.

Other Claude 3 Models

There's Bard, then we've got Sonnet, which is their mid range model. Then we've got another GPT four, and then we've got Haiku. And Haiku is the baby of the Claude three models. It's so cheap. And yet we're seeing here that it outpowers other GPT four models more powerful than Claude two.

Difference Between GPT 3.5 Turbo and Claude 3 Haiku

And yet, look, we have to scroll all the way down to the 14th place to get a GPT 3.5 turbo. And definitely don't quote me on the direct kind of token how many tokens you get. Figures. But you should really do a price comparison and an assessment within your app of the difference between using GPT 3.5 turbo and using Claude three Haiku. Because at least according to these early results, remember that Claude three has only been out for a few days, a few weeks even at this point.

Anthropic as a Competitor to OpenAI

And so you'll see that, you know, Claude has not got as many votes as some of the GPT four preview models. But I've been saying this for a few months now. Anthropic are a serious competitor to OpenAI. And if you have just been using the OpenAI playground to build your prompts, and you've been using Bubble to build no code apps with AI integrated into them, then, yeah, this is your prompt. This is your prompt to go and try out Claude three to try out each of the models available and to see whether you believe that it outperforms OpenAI's GPT models.

Request for Feedback

And I'd really love if you could leave a comment down below if that, if you tried it and disagree with me, I mean, not me, I mean disagree with the very early data that's come out about which is best. Please do, please report your results in the comment section down below because I'd be really interested to know as based on the data, I'm starting to recommend Claude people. I'm saying, have you tried Claude three? Because lots of people, they know chat GPT, they may have heard of OpenAI, they probably haven't heard of Anthropic. So here it is.

Conclusion

Go to Anthropic and try out the Claude three chatbot large language model. And yeah, let me know how your results are going and what sort of feedback you get. And if you're learning Bubble and you're wanting to build no code apps with AI, then follow the link down in the description because we've got hundreds of Bubble tutorial videos where we go really in depth and some beginner content on how to build no code apps with Bubble IO.

Latest videos

crossmenu