4 ways to use AI in your marketing program now

In my latest articlewe saw that artificial intelligence is increasingly able to answer our questions, regardless of the subject or sector.

Using GPT-3 technology, I have shown that an AI can successfully pass an SEO multiple choice test and solve SEO case studies.

There are other, even more advanced technologies, such as Deepmind’s Gopher, which outperform GPT-3 in the following areas: humanities, social sciences, medicine, science, and math.

The following chart shows the accuracy of the answers from Gopher, UnifiedQA, GPT-3, and a human expert.

Depending on the subject, we can narrow the gap between the level of AI and that of an expert†

This also suggests that the AI ​​could potentially exceed the level of a non-skilled person.

Currently, AI can be a useful support resource for many marketing topics.

Let’s take a look at how to work with AI and, more importantly, how to integrate it into your business.

4 ways to interact with an AI tool

We will focus on the key interaction methods to successfully set up the best AI-human combination.

1. Using your web browser

The most interesting form of interaction is to plug in the AI ​​in your back office or in your web browser with a Chrome plugin.

There are countless potential uses as you can help your users with advanced projects such as document classification, writing assistance, meta tag generation, text extraction, and even suggesting new topics.

You can connect the AI ​​to your tools with a simple Javascript call and ask them to perform specific tasks.

Below is an example of a JS integration with GPT-3.

The example is too simplified to show you that with 20 lines of code and the right instructions you can easily connect a language model like GPT-3.

var xhr = new XMLHttpRequest();
xhr.open("POST", 'https://api.openai.com/v1/engines/text-davinci-002/completions');
xhr.setRequestHeader("Content-Type", "application/json");
xhr.setRequestHeader("Authorization", "Bearer sk-RkXXXXXXXXXXXXXXXXXXXXXXXX");
xhr.onreadystatechange = function () {
if (xhr.readyState === 4) {
if (xhr.status==200){
var data=xhr.responseText;
var jsonResponse = JSON.parse(data);
answerGPT3 = jsonResponse["choices"][0]['text'];
console.log(answerGPT3);
}
else {
console.log('API error');
console.log(xhr.responseText);
}
}};
var prompt = "List 50 concepts about … "
var data = `{
"prompt": "PROMPT",
"temperature": 0,
"max_tokens": 256,
"top_p": 1,
"frequency_penalty": 0,
"presence_penalty": 0
}`;
data = data.replace('PROMPT', prompt)
xhr.send(data);

If your back office supports Javascript and you have experienced developers, integrating advanced AI features has never been easier.

To test this first connection, create a Chrome plugin to evaluate an AI for its ability to properly respond to certifications designed for experts.

To do this, use a Chrome plugin that allows optical character recognition to capture all types of text.

Then use a separate Chrome plugin that modifies a page’s CSS to make the page as understandable as possible.

In an example exercise, we assigned each answer of a multiple choice test to a corresponding letter.

Then, with the previous 20 lines of code, we sent the instructions to the AI ​​to generate the results in a text field.

With this program, called “Asimov’s tests”, the AI ​​managed to achieve several certifications.

I then tested the AI ​​in the field of medical science and achieved scores of over 60%, with no prior training in any specific discipline.

This confirms that by choosing your topic correctly, the results of the AI ​​can greatly help your teams improve their day-to-day work.

2. Using your data visualization tools

In recent months, tools have emerged that generate documentation or facilitate writing code.

One notable use case is to easily generate dashboards or SEO tools with instructions.

There are now open source tools like streamlined with highly advanced components in Data visualization or data manipulation.

By providing the right instructions, it is easy to request the generation of an app that communicates directly with your data.

For example, you can generate a web application with a complete interface and functional code.

This practice is quite recent, as we use language models that are fed solely by computer code. And again, the results are quite impressive.

The following chart shows all the most popular code generators and the data they were created with.

• Code Parrot: 50 GB.
• GPT-3 codex: 159 GB.
• Incoder: 216 GB.
• PolyCoder: 249 GB.
• Alpha code: 715.1 GB.
• CodeGen: 1.38 TB.

It is possible to generate applications in many languages; the main ones are Java, C, JS and PHP.

Whether you’re a novice or an expert, I encourage you to give it a try – the AI ​​can create your SQL query or your graphs in a matter of seconds.

Practical use is important if you want to get better at using your favorite tools.

3. Using a chatbot

You can also create a chatbot to answer very specific questions by clearly stating its role in the instructions.

Here I ask the chatbot to respond as if it were a doctor, while also using a touch of friendliness and humor.

AI-based chatbots can therefore provide personalized advice and recommendations based on customer preferences. Don’t hesitate to adjust the AI ​​to react in a certain way.

A good example is Danny Richman, who created an AI version of Google’s John Mueller called MuellerBot.

This bot builds on the above principle of answering SEO questions as if John Mueller was answering them himself.

It’s both fun and disturbing, because the answers can be quite accurate.

Image by Danny Richman, June 2022

4. Using an AI Assistant Program

Finally, AI assistants for SEO are programs that run in the background and apply SEO fixes if a page is poorly constructed or has classic errors.

The first such applications date back to 2016, when Facebook was still implement automatic bug fixes with Getafix†

Based on all the bugs that have been fixed in the past, the assistant prepares correction templates that are applied and reviewed by a human before being rolled out.

This is very applicable in SEO where we know that concerns about meta tag titles, descriptions, pagination and links are typical issues.

To do this, you can use GPT-3 in edit mode and customize the SEO pages using the appropriate instructions.

Below are my instructions:

• Add a title with an H1 tag at the beginning of the text.
• add a -link to the most important word in the body of the text.
• Create useful outlinks at the end of the text using
  • †
  • Include a YouTube video in the body of the text.
  • Put the top five concepts in bold.

  Screenshot of OpenAI, June 2022

  Examining the generated text, we can see that the results are excellent: the H1 title summarizes the article, the words in bold are accurate, and the YouTube video and outbound links are relevant to the theme.

  Screenshot of OpenAI, June 2022

  In short, your AI assistant can save you a lot of time.

  Just a note: the links are all dummy links, but you can connect anything to a link database and use mapping tables to replace LINK1 with a link in your database or CSV file.

  Now you can appreciate the potential of automating these types of tasks.

  Now that you know the different ways to associate a language model with your existing tools, don’t hesitate to implement the method(s) that work best for you, such as:

  • Chrome plugin.
  • Directly in your CMS.
  • Through a chatbot.
  • Data visualization.
  • AI assistant.

  More resources:

  ---

  Featured Image: Graphic Farm/Shutterstock