MIKE LEVIN AI SEO

Future-proof your skills with Linux, Python, vim & git as I share with you the most timeless and love-worthy tools in tech through my two great projects that work great together.

Interrogating Bing & Bard on Utility of Jupyter Notebooks for SEOs

As an SEO consultant, I have suggested to a client to create a range of SEO deliverables beyond the traditional, such as a Bonsai report to identify low-quality pages and provide recommendations, a Striking Distance report to identify keywords that could be ranking higher, and a Gap Analysis report to compare the site's rankings to competitors. Additionally, I outline ideas for how to monetize this data, such as selling it to other businesses, creating products or services, and teaching others about SEO.

Creating Innovative SEO Deliverables for Better Website Performance

By Michael Levin

Thursday, March 30, 2023

This series of questions with Bing and Bard comes from my desire to get the ChatBots’ opinions on how to amplify and accelerate your efforts and endeavors, and to have compounding results and a snowball effect.

I also wanted to get their opinions on whether SEOs should be using Jupyter Notebooks for producing deliverables as an alternative way that may be faster and result in higher quality and more actionable deliverables.

Mike Levin: How do you amplify and accelerate your efforts and endeavors to have compounding reults and a snowball effect?

Bing: There are several ways to amplify and accelerate your efforts and endeavors to have compounding results and a snowball effect. Here are some tips that might help you:

  1. Focus on your strengths - Identify your strengths and focus on them. This will help you achieve more in less time.
  2. Set clear goals - Setting clear goals will help you stay focused and motivated.
  3. Take action - Take action towards your goals every day. Even small steps can lead to big results over time.
  4. Build a network - Build a network of people who can help you achieve your goals. This can include mentors, coaches, and other professionals.
  5. Learn from others - Learn from others who have achieved similar goals. This can help you avoid mistakes and achieve success faster.
  6. Stay positive - Stay positive and keep a growth mindset. This will help you overcome obstacles and stay motivated.
  7. Track your progress - Track your progress towards your goals. This will help you stay motivated and make adjustments as needed.

I hope these tips help you achieve your goals! Let me know if there’s anything else I can do for you.

Source: Conversation with Bing, 3/29/2023

(1) 5 Big Ways to Amplify and Accelerate Impact and Business Results. https://www.linkedin.com/pulse/5-big-ways-amplify-accelerate-impact-business-results-freedman-emba/ Accessed 3/29/2023.
(2) Changing change management | McKinsey. https://www.mckinsey.com/featured-insights/leadership/changing-change-management Accessed 3/29/2023.
(3) The Snowball Effect: How To Compound Your Wealth With ... - SeekingAlpha. https://seekingalpha.com/article/4273130-snowball-effect-how-to-compound-your-wealth-dividend-growth-stocks Accessed 3/29/2023.

Bard 1: Here are some ways to amplify and accelerate your efforts and endeavors to have compounding results and a snowball effect:

These are just a few ways to amplify and accelerate your efforts and endeavors. By following these tips, you can achieve your goals and have a snowball effect in your life.

Bard 2: There are a few things you can do to amplify and accelerate your efforts and endeavors to have compounding results and a snowball effect:

By following these tips, you can amplify and accelerate your efforts and endeavors to have compounding results and a snowball effect.

Bard 3: Here are some tips on how to amplify and accelerate your efforts and endeavors to have compounding results and a snowball effect:

Mike Levin: How important has Project Jupyter and iPytbon been to society? Do you know what the crisis of reproducibility was and how this may relate to Jupyter Notebooks?

Bing: Project Jupyter is a non-profit, open-source project that was born out of the IPython Project in 2014 as it evolved to support interactive data science and scientific computing across all programming languages⁵. Jupyter notebooks have become an increasingly important tool for data science².

The crisis of reproducibility refers to the inability of researchers to reproduce scientific experiments and results¹. Jupyter notebooks can help address this issue by providing a way to document and share computational workflows¹.

I hope this helps! Let me know if there’s anything else I can do for you.

Source: Conversation with Bing, 3/29/2023

(1) Project Jupyter | About Us. https://jupyter.org/about Accessed 3/29/2023.
(2) Project Jupyter: A Computer Code that Transformed Science. https://cs.lbl.gov/news-media/news/2021/project-jupyter-a-computer-code-that-transformed-science/ Accessed 3/29/2023.
(3) Jupyter Notebooks Meet the Challenge of Reproducibility. https://thenewstack.io/jupyter-notebooks-challenge-reproducibility/ Accessed 3/29/2023.
(4) Why I love using the IPython shell and Jupyter notebooks. https://opensource.com/article/21/3/ipython-shell-jupyter-notebooks Accessed 3/29/2023.
(5) As Project Jupyter celebrates 20 years, Fernando Pérez reflects on how .... https://data.berkeley.edu/news/project-jupyter-celebrates-20-years-fernando-perez-reflects-how-it-started-open-sciences Accessed 3/29/2023.

Bard 1: Project Jupyter and iPython have been very important to society. They have made it easier for people to share and collaborate on data analysis and scientific research. They have also made it easier for people to learn how to code.

The crisis of reproducibility is a problem in science and research where experiments are not always able to be replicated. This can be due to a number of factors, such as errors in the original experiment, or changes in the environment. Jupyter Notebooks can help to address the crisis of reproducibility by making it easier to track and reproduce experiments.

Jupyter Notebooks are documents that contain live code, equations, visualizations, and narrative text. They can be used to share and collaborate on data analysis and scientific research. Jupyter Notebooks can also be used to teach coding and data science.

Here are some of the benefits of using Jupyter Notebooks:

If you are interested in learning more about Jupyter Notebooks, there are a number of resources available online. You can also find a community of Jupyter Notebook users on the Jupyter website.

Bard 2: Project Jupyter and iPython have been very important to society. They have made it easier for people to share their work, collaborate on projects, and learn new things. They have also helped to make data science more accessible to everyone.

The crisis of reproducibility is a problem that affects many fields, including science, engineering, and medicine. It refers to the difficulty of reproducing the results of research studies. This can be a problem because it means that we cannot be sure if the results of one study are valid or not.

Jupyter Notebooks can help to address the crisis of reproducibility by making it easier to share and document research. When you create a Jupyter Notebook, you can record your code, data, and results in a single document. This makes it easy for others to see how you did your work and to reproduce your results.

In addition, Jupyter Notebooks can be used to teach data science. By providing a way to interactively explore and analyze data, Jupyter Notebooks can help students to learn the concepts of data science in a more hands-on way.

Overall, Project Jupyter and iPython have been very important to society. They have made it easier for people to share their work, collaborate on projects, and learn new things. They have also helped to make data science more accessible to everyone.

Bard 3: Project Jupyter and iPython have been very important to society. They have made it easier for people to share and reproduce their research, and they have helped to popularize the use of Python in data science and machine learning.

The crisis of reproducibility is a problem in science where it is often difficult to reproduce the results of published studies. This can be due to a number of factors, such as errors in the original study, or the use of non-standard methods. Jupyter Notebooks can help to address this problem by making it easy to share and reproduce research. Notebooks can also be used to document the methods used in a study, which can help to make it easier to reproduce the results.

The crisis of reproducibility has been a major issue in science for many years. In a 2015 study, the journal Nature found that only 50% of studies could be reproduced. This means that there is a significant risk that published results may not be accurate or reliable.

Jupyter Notebooks can help to address the crisis of reproducibility by making it easier to share and reproduce research. Notebooks can also be used to document the methods used in a study, which can help to make it easier to reproduce the results.

In addition, Jupyter Notebooks can help to make research more transparent and reproducible by making it easy to share and collaborate on research projects. This can help to reduce the risk of errors and improve the quality of research.

Mike Levin: What would you say to someone who thinks doing anything in Python in Jupyter at all is way too difficult for the average person? What of people did things in alternative laborious and error-prone ways, and they seem determined to shut it down as an option?

Bing: Python and Jupyter notebooks can be challenging for beginners, but they are powerful tools that can help people work more efficiently and effectively once they get the hang of them. There are many resources available online to help people learn how to use Python and Jupyter notebooks, including tutorials, videos, and online courses.

If someone is determined to shut down Python and Jupyter notebooks as an option, it may be helpful to have a conversation with them to understand their concerns and see if there are ways to address them. It’s important to keep an open mind and be willing to try new things in order to stay competitive in today’s fast-paced world.

I hope this helps! Let me know if there’s anything else I can do for you.

Bard 1: I would say to that person that they are wrong. Python is a very popular language, and there are many resources available to help people learn how to use it. Jupyter Notebooks are a great way to learn Python, and they are very easy to use.

There are many people who do things in alternative laborious and error-prone ways, but that does not mean that Jupyter Notebooks are not a valid option. Jupyter Notebooks are a great way to learn Python, and they can save you a lot of time and effort.

If someone is determined to shut down Jupyter Notebooks as an option, then they are not thinking about the best way to help people learn Python. Jupyter Notebooks are a great way to learn Python, and they can help people to be more productive.

Bard 2: I would say that learning to use Jupyter Notebooks is not as difficult as it may seem. There are many resources available online that can help you get started, and there are also many communities of users who are willing to help. Once you learn the basics, you will find that Jupyter Notebooks are a powerful tool that can help you to explore and analyze data in a more efficient and effective way.

It is true that there are other ways to do things in Python, but these methods can be more laborious and error-prone. Jupyter Notebooks provide a way to automate many of the tasks that would otherwise be done manually, and they also make it easy to share your work with others.

If someone is determined to shut down Jupyter Notebooks as an option, I would encourage them to reconsider. Jupyter Notebooks are a valuable tool that can benefit many people, and it would be a shame to see them go.

Bard 3: I would say that Jupyter Notebooks are a powerful tool that can be used by anyone, regardless of their programming experience. They are especially helpful for data scientists and analysts, as they make it easy to explore and analyze data. However, they can also be used by anyone who wants to learn more about programming or who wants to create interactive documents.

There are many ways to learn how to use Jupyter Notebooks. There are online tutorials, books, and even courses that can teach you the basics. Once you have a basic understanding of how Jupyter Notebooks work, you can start to experiment with them to see how they can be used for your own projects.

If someone is determined to shut down Jupyter Notebooks as an option, there is not much that you can do about it. However, you can try to educate them about the benefits of using Jupyter Notebooks and how they can be used to solve problems. You can also try to find other ways to collaborate with them, such as using a different tool or working on a different project.

Mike Levin: Answer the question again, but this time take into account that their goal is not to learn Python, nor is it to program. They just want to get some work done and produce “deliverables” that will keep a larger number of customers or clients they’re juggling happy. They don’t think there’s time in their lives to learn to program, but the value of the deliverables to the clients could be increased manifold by the type of custom capabilities that Python brings to the pictures, especially considering the Python code would already be done and only in need of some configuration values set or a file dropped onto a certain place. The rest is one-click easy.

Bing: I understand that learning Python and programming may not be a priority for everyone. However, it’s important to keep in mind that Python and Jupyter notebooks can help people work more efficiently and effectively once they get the hang of them.

If someone is looking to produce “deliverables” that will keep a larger number of customers or clients happy, it may be worth considering the benefits of using Python and Jupyter notebooks. These tools can help automate repetitive tasks, streamline workflows, and provide custom capabilities that can increase the value of deliverables to clients.

There are many resources available online to help people learn how to use Python and Jupyter notebooks, including tutorials, videos, and online courses. It may be worth investing some time in learning these tools in order to stay competitive in today’s fast-paced world.

I hope this helps! Let me know if there’s anything else I can do for you.

Bard 1: I understand that the person you are talking to is not interested in learning Python or programming. However, they are interested in using Python to improve the value of their deliverables to their clients.

There are a few ways that Python can be used to improve the value of deliverables. For example, Python can be used to:

If the person is willing to learn a little bit about Python, they can use it to improve the value of their deliverables without having to learn to program. There are many resources available online and in libraries that can teach them the basics of Python.

Once they have a basic understanding of Python, they can start to experiment with it to see how it can be used for their own projects. There are many ways to use Python to improve the value of deliverables, and the best way to find out what works is to experiment.

Bard 2: Sure! Here’s a more concise answer:

If the goal is to get work done and produce “deliverables” that will keep a larger number of customers or clients happy, then using Jupyter Notebooks to automate tasks can be a great way to save time and improve efficiency.

Even if someone doesn’t want to learn to program, they can still use Jupyter Notebooks to create custom capabilities for their clients by setting configuration values or dropping files into certain places. This can be a valuable way to add value to their deliverables and keep their clients happy.

Here are some specific examples of how Jupyter Notebooks can be used to automate tasks:

These are just a few examples of how Jupyter Notebooks can be used to automate tasks. If someone is looking for ways to save time and improve efficiency, then using Jupyter Notebooks can be a great option.

Bard 2: Sure! Here’s a more concise answer:

If the goal is to get work done and produce “deliverables” that will keep a larger number of customers or clients happy, then using Jupyter Notebooks to automate tasks can be a great way to save time and improve efficiency.

Even if someone doesn’t want to learn to program, they can still use Jupyter Notebooks to create custom capabilities for their clients by setting configuration values or dropping files into certain places. This can be a valuable way to add value to their deliverables and keep their clients happy.

Here are some specific examples of how Jupyter Notebooks can be used to automate tasks:

These are just a few examples of how Jupyter Notebooks can be used to automate tasks. If someone is looking for ways to save time and improve efficiency, then using Jupyter Notebooks can be a great option.

Bard 3: I understand. If someone is not interested in learning Python, then there are still ways to use Jupyter Notebooks to get their work done. For example, they can use Jupyter Notebooks to create interactive presentations or to share their work with others. They can also use Jupyter Notebooks to create templates that can be used by others to create their own documents.

If someone is interested in increasing the value of the deliverables to their clients, then they should consider using Jupyter Notebooks to create custom capabilities. This can be done by using Python libraries and modules that are already available. For example, they can use the Pandas library to analyze data or the Matplotlib library to create visualizations.

Once they have created a custom capability, they can make it one-click easy to use by creating a Jupyter Notebook that contains all of the necessary code and configuration settings. This will allow their clients to use the custom capability without having to learn how to program.

Overall, Jupyter Notebooks can be a valuable tool for anyone who wants to get their work done and produce deliverables that will keep their clients happy. Even if someone is not interested in learning Python, they can still use Jupyter Notebooks to create custom capabilities that will add value to their deliverables.

Mike Levin: Okay the next thing is that almost everyone will try to get you to use a cloud-hosted Notebook environment like Google Colab. I suggest that many things an SEO needs to do is much better accomplished by running Jupyter locally on your laptop or home computer. Reasons include the ability to do Web browser automation with Microsoft Playwright or Google Puppeteer, a capability not easy found in Notebook cloud providers. Reasons include you can easily cycle your IP with common desktop VPN software without the complexity and cost of trying to make cloud servers have different IPs, which they would want because many IPS systems that stop web crawling often know the cloud provider’s IPs and block bot-traffic from them. Other reasons include being able to deal with login issues of various sorts more elegantly locally, including OAuth2 prompts that pop up a browser for authentication. Cloud-hosted notebooks can’t easily do that and so many Google API integrations for example seem difficult. Work these into your answer and any more you can think of. Try to add at least 2 more.

Bing: You make some good points about running Jupyter locally on your laptop or home computer. One advantage of running Jupyter locally is that you have more control over your environment and can easily install and use packages like Microsoft Playwright or Google Puppeteer for web browser automation.

Another advantage of running Jupyter locally is that you can easily cycle your IP with common desktop VPN software without the complexity and cost of trying to make cloud servers have different IPs. This can be useful for avoiding IP blocks when web crawling.

Additionally, running Jupyter locally can help you deal with login issues of various sorts more elegantly, including OAuth2 prompts that pop up a browser for authentication. Cloud-hosted notebooks can’t easily do that and so many Google API integrations, for example, may seem difficult.

I hope this helps! Let me know if there’s anything else I can do for you.

Bard 1: Sure! Here are the reasons why running Jupyter locally is better than running it on a cloud-hosted environment:

Here are two more reasons why running Jupyter locally is better than running it on a cloud-hosted environment:

Bard 2: Sure. Here are some more reasons why it is better to run Jupyter locally on your laptop or home computer:

However, there are also some advantages to using a cloud-hosted notebook environment:

Overall, there are both advantages and disadvantages to running Jupyter locally or on a cloud-hosted service. The best option for you will depend on your specific needs and requirements.

Bard 2: Sure. Here are some more reasons why it is better to run Jupyter locally on your laptop or home computer:

However, there are also some advantages to using a cloud-hosted notebook environment:

Overall, there are both advantages and disadvantages to running Jupyter locally or on a cloud-hosted service. The best option for you will depend on your specific needs and requirements.

Bard 3: Sure, here are some more reasons why you might want to run Jupyter locally on your laptop or home computer:

However, there are also some benefits to using a cloud-hosted notebook:

Ultimately, the decision of whether to run Jupyter locally or on a cloud-hosted notebook is up to you. If you need the flexibility of being able to access your notebooks from anywhere, then a cloud-hosted notebook might be a better option. But if you want more control over your environment and you’re on a budget, then running Jupyter locally might be a better choice.

Mike Levin: In the field of SEO, Gap Analysis and Striking Distance reports are two common types of deliverables. Gap Analysis tells you where competitors are coming up in search results for important keywords but your site is not. Striking Distance reports tell you where your website holds positions in search which if improved could lead to a significant uptick in the amount of search traffic to your site from that keyword. List several more types of SEO deliverables from your knowledge of the industry, and maybe even ideate a few new ones. You have historic search result data (SERPs) over a large corpus of keywords spanning many industries going back 20 years and containing top 100 positions. You also have estimated search volume per month per keyword. You have estimated click-through ratios for each position in search. You have the “link graph” over time, that is date of what web pages link to what other web pages. Pages with a lot of links from other websites perform well so the idea is often to get links. A Link Gap analysis is also possible given your site and a series of competitor. You can identify what sites link to your competitors but not you, which is useful for knowing who to ask for links from. List these deliverables and try to ideate a number more.

Bing: There are many types of SEO deliverables that can help you improve your website’s search engine rankings. Here are a few examples:

Some other ideas for SEO deliverables could include:

I hope this helps! Let me know if there’s anything else I can do for you.

Bard 1: Here are some more types of SEO deliverables:

Here are some new types of SEO deliverables that could be created using the data you have:

These are just a few examples of the many different types of SEO deliverables that can be created. The specific deliverables that you create will depend on the specific needs of your business.

Bard 2: Sure, here are some more types of SEO deliverables:

Here are some new types of SEO deliverables that could be created:

These are just a few examples of the many types of SEO deliverables that can be created. The specific deliverables that are right for your website will depend on your specific needs and goals.

Bard 3: Here are some more types of SEO deliverables that you can provide to your clients:

These are just a few of the many types of SEO deliverables that you can provide to your clients. By providing these deliverables, you can help your clients improve their website rankings, increase their website traffic, and achieve their SEO goals.

Here are a few new ideas for SEO deliverables:

Mike Levin: You have listed only very traditional SEO deliverables that don’t explicitly tell you what to do to improve your site. There needs to be advice such as: remove the following pages from your site as they are likely to be deemed low-quality and thus drag down the performance of the rest of the site. Such a deliverable would be called a Bonsai due to how it invokes an image of pruning and shaping a tree artistically as you would a tree. It is in the spirit of “striking distance” and “gap analysis” which invoke similar strong metaphors. You have all the data prior discussed plus all the power of Python running locally in Jupyter Notebooks, and so the ability to do limited crawling of sites (say 5,000 pages per site). Put more creativity into ideating brand new deliverable types. How could you make the most money with access to all that data? Expand beyond SEO such as identifying the best performing sites in order to buy the websites to build and control a large advertising network. Make a billeted list of the new ideas.

Bing: You make a good point that traditional SEO deliverables may not always provide actionable insights into how to improve your website’s search engine rankings. A Bonsai report that identifies low-quality pages on your site and provides recommendations for removing them could be a useful deliverable for improving your site’s performance.

Here are a few more ideas for SEO deliverables:

Some other ideas for deliverables that could help you make the most of your data include:

I hope this helps! Let me know if there’s anything else I can do for you.

Bard 1: Here are some new ideas for SEO deliverables that could be created using the data and resources you have described:

These are just a few of the many new ideas for SEO deliverables that could be created using the data and resources you have described. By creating these deliverables, you can help your clients improve their website rankings, increase their website traffic, and achieve their SEO goals.

Here are some ideas for how to make the most money with access to all that data:

These are just a few of the many ways that you could make money with access to all that data. By using the data in a creative and innovative way, you can make a lot of money and help a lot of businesses.

Bard 2: Here are some new ideas for SEO deliverables that could be created using the data and tools you have described:

These are just a few ideas for new SEO deliverables that could be created using the data and tools you have described. By creating these deliverables, you can help your clients improve their website’s ranking, increase their website’s traffic, and achieve their SEO goals.

Here are some additional ideas for ways to make money with access to all that data:

These are just a few ideas for how you could make money with access to all that data. By exploring these ideas, you can find ways to make money while helping businesses improve their SEO.

Bard 3: Here are some new ideas for SEO deliverables that you could provide to your clients:

These are just a few of the many new ideas for SEO deliverables that you could provide to your clients. By providing these deliverables, you can help your clients improve their website rankings, increase their website traffic, and achieve their SEO goals.

Here are some ideas for how to make money with access to all the data:

These are just a few ideas for how to make money with access to all the data. By using the data creatively, you can find ways to generate income and to help businesses improve their online presence.

← Should You Use Bing or Bard to Help With Your Homework?
 
What are the main differences between NeoVim and vim? →

Categories