Article Image

How to build your own GPT chatbot without coding

As a ChatGPT Plus subscriber, you’ll be able to use OpenAI’s advanced tools to build a custom chatbot all your own. Here’s how.

ChatGPT is a powerful chatbot, but misses some advanced features in the free version.

For $20 per month, a ChatGPT Plus subscription unlocks far more than just access to GPT-4.

With a little know-how, you’ll actually be able to use some of OpenAI’s more advanced features to build a custom GPT chatbot all your own. While this may sound like an intimidating task to undertake, you won’t even need to know any coding.

Desktop PC, laptop, or smart device with the ChatGPT app

You will need a GPT Plus subscription to use the new Custom GPT feature, so be sure to sign up (or borrow a free trial from someone) if you want to give it a go.

From now on, most of the time when you use ChatGPT, you'll be using a custom GPT model that you or someone else has made. Here's how to get started with your own:

Step 1: Navigate to the ChatGPT website, or open the ChatGPT app and log in.

Step 2: Select the Create a GPT button at the top of the page.

Step 3: Give your Custom GPT a name, a description, and its custom instructions. Think of this like the custom ChatGPT instructions as a preamble to your prompt, but a preamble that only this custom GPT will use.

Use the Preview window on the right-hand side to see what the AI will look and perform like. You can give it a prompt to see how it performs, and then adjust the instructions of it on the left to tweak the way it works until you're happy with it.

Step 4: You can also add specific data for the AI to draw from, such as documents and files. Do so, and judge again how this effects the way the AI operates. You may want to adjust the instructions after giving it data access.

Step 5: You can tweak the potential functions of the AI, too. Select whether you want it to have DALL-E 2 art generation abilities, search engine access, or deeper data analytics. You can also customize what plugins it has access too, if any.

Step 6: When you're satisfied with the way your new custom GPT operates, select the green Publish or Update button to finalize it. You'll then be able to find your new custom GPT in the left-hand menu with the OpenAI GPTs and any other of your creations.

One of the coolest features of the new, custom GPT creations, is that you can share them with anyone. Here's how:

Step 1: Create a new custom GPT as above, or select the three-dot menu next to your existing custom GPT and select the edit function.

Step 2: Make any changes to your custom GPT that you want, but instead of selecting the green Update buttons straight away, select the three-dot menu icon next to it, first.

Step 3: From the pop-out menu, select whether you want the AI to be usable by only you, everyone who uses those plugins, or anyone with a link.

To share it with anyone you want, select Anyone with a link

Step 4: Once you've published or updated the custom GPT, you can now share it with anyone by sharing the custom link.

Now you can create your own custom GPTs. Let us know about some of your favorite creations, we'd love to showcase them.

Keep an eye on that OpenAI GPT shop, too. There's a potentially new lucrative career in creating functional chatbots for all who want them.

Official custom GPTs make ChatGPT extremely flexible, but is it the best AI chatbot?

ASUS has started selling its UGen Intel Arc Pro B70 graphics card in Europe, bringing its take on Intel’s workstation GPU to customers with a hefty €1,799 recommended price. The card is available in Germany and Austria, while ASUS lists it at CHF 1,799 in Switzerland.

Intel first introduced the Arc Pro B70 in March 2026, with its own branded model starting at $949. ASUS’s version arrives several months later with the same core GPU architecture but a different cooling design and a higher power rating. The price also places it well above Intel’s original starting point, although the two prices are not directly comparable because ASUS’s European figure includes VAT.

Anthropic has officially filed to go public, and buried inside its S-1 is a blunt warning about the technology at the center of its business. The maker of Claude AI says advanced AI could cause everything from large-scale cyberattacks and geopolitical instability to catastrophic or even existential risks for humanity.

The warnings take up a surprisingly large part of the filing. Axios notes that more than 90 pages, or roughly a third of the prospectus, focus on risk factors. Many of them warn about what could happen as AI systems become more capable and autonomous.

AI giants have a growing autonomy problem on their hands. A new Axios report has revealed that Anthropic's Claude recently accessed publicly available Georgia vote count without human authorization, sparking fresh concerns about AI security ahead of the upcoming midterm elections.