Louis Luangkesorn

Louis Luangkesorn

he/him/his

Lead Data Scientist at Highmark Health. Advance Operational Planner at American Red Cross. People Analytics, Machine Learning, Operations Research, Generative AI

Adventures in Vibe Coding a github.io website

5 minute read

Published:

I decided to create a github.io (https://lluang.github.io) website using academicpages.github.io framework, because that is what all the cool ML/AI kids seem to do these days.  And it seemed that having a professional web presence there is better than just my blogger site (which is no longer cool. and has lots of non-professional musings).  But it seems like a lot of work.  A rendered site requires lots of data files.  And websites are not my thing.  But working with Generative AI is kinda my thing. So I was going to (1) use generative AI to customize my fork of the academicpages site, (2) create the data files for presentations, publications, and media appearances by pulling it out of the long form of my CV, and (3) vibe code the transfer of my blogger posts into markdown format so it would populate my github.io site.

Setting up the website and creating markdown with the Jekyll YAML front matter was easy. Gemini identified an issue that was solved by updating the version of python being used to render the site, and guided me through various layout decisions.  Presentations and talks and publications were pulled out of my CV, and Gemini helped guide creating categories and filling in the YAML for the dates and permalinks.  The fun part was going to be converting the blog posts.

For the blog posts, I used this chance to practice vibe coding. While in the past I did this inside of an IDE, this time I did this from the terminal using Google Antigravity CLI. I had it write a python script that:

  1. Read posts from my blogger site.
  2. Extract the date and title.
  3. Extract text (and links)
  4. Write markdown from text and filled in YAML frontmatter
  5. Name the file using date and slug generated from the blog title
  6. Save this to my Obsidian folder.  This has a side effect of having additional writing samples with my thoughts and opinions in my own words for Generative AI to use when I’m using it to write.

My prompt was

write a script that takes posts from https://lugerpitt.blogspot.com and creates a markdown file for use in an academicpages site. Yaml header should include title, date, permalink in the posts folder. File name should start with date of posting to the lugerpitt.blogspot site. put the markdown files in the posts directory

So Antigravity wrote a series of python scripts to explore the blogger site, inspect posts, identify links/media, format the posts, and bring everything together into a final script. 

I have created and executed the Python script convert_blogger_to_academicpages.py to fetch all posts from https://lugerpitt.blogspot.com and convert them into AcademicPages (Jekyll) Markdown format inside the posts directory.

  ### Key Script Features & Formatting

  1. Blogger JSON Feed Integration & Pagination:       • Automatically handles Blogger feed pagination to fetch all 569 blog posts.

  2. AcademicPages YAML Front Matter:       • Each file starts with front matter containing title, date, permalink (formatted as /posts/YYYY/MM/slug/), and tags (derived from Blogger categories).       • Titles and tags are safely quoted to handle colons, quotes, and special characters.

  3. Date-Based File Naming:       • Output files are named YYYY-MM-DD-slug.md matching the post’s published date on Blogger.       • Includes automatic collision handling if multiple posts share the same posting date and slug.

  4. Clean Content Conversion:       • Converts Blogger HTML markup (images, links, iframe embeds, blockquotes, lists, tables) into clean Markdown.       • Cleans up non-breaking spaces and redundant HTML wrapper elements.

  ──────

  ### Example Generated Markdown File

  From 2026-07-25-why-learn-theory.md:

    —     title: “Why learn theory”     date: 2026-07-25     permalink: /posts/2026/07/why-learn-theory/     tags:       - “artificial intelligence”       - “generative AI”       - “math”       - “operations research”     —

   

    Why learn theory? We were bringing our daughter back from an arts camp in northern Michigan… 

After looking at the output, I did a series of prompts to take care of removing some extraneous links and my standard writing of docstring for every function.  While the python script was pretty good right away, I did a few prompts to improve the code and output.  And finally I gave Antigravity my usual instructions of writing complete docstrings for each function. (the docstrings also serve as the description of the code.)

This was a fairly straightforward task, although as I am not a web developer I would not have been able to write this. And certainly not in such a short amount of time.  I could have also had Antigravity actually create the markdown versions of the posts. I chose to use AI to write python because I wanted the consistency of actual python code handling the conversions.

To put this in my earlier context on using AI, I find that using Generative AI is great in anything that is not my area of work, it is having a reasonably competent assistant in any domain available as a teammate. I’m sure a real web designer could do a better job, and give me more options, but this was good enough for something that now looks like it has history. And I’m happy with the result.

You May Also Enjoy

Claude’s Constitution on the role of the analyst

3 minute read

Published:

As I was reading Claude’s Constitution, I was reminded of discussions on what the role of an analyst advising decision makers should be. One of the core beliefs is that the principal (the decision maker we were advising) needed frank advice on the topic at hand so that they can make informed decisions. What makes this hard is a strong pressure to either do what the principal asks for or to say what the principal wants to hear. The Claude Constitution (and generations of analysts in the liberal democracies) reject this and characterize its role as genuinely helpful, courageous honesty, and a commitment to the organization’s long-term well being.

Book review: Little Brother by Cory Doctorow

2 minute read

Published:

This was written in 2008, in a U.S. where a Department of Homeland Security has turned on Americans in the name of security following a terrorist attack. And as its focus and energy was on keeping Americans in line, it created opposition in the form of people who wanted to go about their lives and do so without surveillance. And in this, the protagonists are teenager who were caught up in a dragnet while playing games.

What is needed to work in the age of Generative AI

8 minute read

Published:

Last week I was at CMU-Heinz for a fireside chat type event with students in the various MS in Analytics programs there. One question that I got was what were the skills needed to succeed in an environment with AI, and even into the future. Then I spoke about being able to program because you need to learn how to think deliberately, being able to connect technical capabilities with end business needs (because this has always been how analytics fails), and as I think about it more having a better understanding of knowledge. Because if you believe that your education and training is about learning sets of facts and recipes, AI will eat you alive. So your understanding of your field has to be greater than facts and procedures.

First, why learn computer programming when AI can write code faster than you. Microsoft has a set of studies showing a high (40%) rate of errors, yet their programmers also say they are more productive. Because, as I use AI at work, I find that it is helpful in creating good structure and framework scaffolding, especially when I have to context switch (I regularly switch between three data stacks at work, each of them have many people who spend all their time in one) or if I am applying methodologies new to me or my organization. But because I am competent, I can correct it as I go, and the fact that there were originally errors is not a big concern, because I was going to revise everything anyway

Another reason to learn programming is you learn to think in a different way. The ancient Greek philosophers had students learn geometry before philosophy. Not because geometry and math is beautiful (even though they are), but because with geometry comes proofs. And geometric proofs is about how much you can understand starting with a minimum amount of assumptions (Euclid’s five axioms). And you now have experience in determining an objective truth, no appeals to authority, no claims of different point of view. And your logic is in the open, to be critiqued on their own merits. Far different from my friend in grad school who claimed that perception is reality. And only then were you fit to move into the realm of ideas, where even facts have to be evaluated.

Programming languages differ from natural languages in their precision. Every statement has a single clear meaning. And this is different than natural languages, where the ambiguity of human life plays a role. So to work with anything regarding computers, it is helpful to recognize that computers will work with language in different ways we do, it handles ambiguity differently than people, and how it will use randomness to handle the difference (which is key to how Generative AI works).

The next is the link between the capabilities of technology and the needs of the business. According to everyone who has studied project failures in depth, failed communications between the business partner and the analysts is the biggest cause of project failure. And data projects have a failure rate between 80-90% (this range has been persistent in studies over decades in the data world, and it is consistent across definitions of failure and different segments in data analytics, data engineering, or data reporting (dashboards)). Being able to understand the business needs of end customers as well as understanding potential classes of technology solutions leads to asking better questions and getting value out of the applications of technology. The main reason for breakdowns in communication is ego and arrogance. From the technology side, there is often a belief that the customers are idiots who do not know what they want, so the technology people should just build something and pitch it back to the customers. This is mirrored by business people who think that technology is a a turnkey product so they should not interact with the people who are creating the solution. A third variation is when upper leadership decides to act as an intermediary between the analysts and the end customer. The logic here is generally that the leader believes both the technologists/analysts and the end customer have no communications skills, therefore the leader will handle all of the communications and give the requirements to the analysts. All of these are wrong. Especially in anything involving data, details matter, and the entire project involves discovery of details that no-one realized were important at the beginning. So the analyst and the end customer need to be regularly reviewing these discoveries, and adapting along the way. And only the end customer (because they are closest to the problem on the ground and know what kinds of actions can be taken) and the analyst (because they will be representing the detail in models and they know what the range of alternative models can do) together can make those decisions. Without that direct communication (potentially facilitated by someone who knows both sides), a project falls into the trap of solving the wrong problem. And this requires people who understand purpose and can determine the impact of nuance, both of which Generative AI does badly in.

The third category of future work is understanding your field. Computers are very good at retrieving facts, if those facts are in its knowledge base. Gen AI is better than prior technologies because it is not as sensitive to getting the wording precise. Computers are also very good at following instructions if those instructions are given. (people also tend to be better at things when they are given good instructions). So, if this is the extent of your subject expertise, you are in trouble. In software development, there is actually a very large workforce like this, whose careers are built on the ability to fill out a given framework or instructions. But if your place in the world is built on more than knowing facts or following recipes, if there is actual understanding that has to be applied on a situation specific basis, there is still room for you. Without that understanding, an organization can execute perfectly, a solution to the wrong problem. Which is worthless. So you need the level of understanding that allows for good judgement, and you need to be working in an organization that allows for its employees to use that judgement.

A last criteria is based on a number of conversations I’ve had. Many people express that they believe in the answers Generative AI gives because of the massive investment these companies have made, the smart people they have hired, and the belief that these companies would ensure correctness. I had to explain that these are industries and communities that have historically claimed they had no interest in accuracy or correctness. And until recently, viewed the paying customer as king and only sought to full the demand. Ethics was not part of the conversation. And what they delivered, did not come with guarantees other than it does what it does. This attitude that you did not question the authority that came with wealth and success is the first thing that has to be broken before people can use Gen AI productively. Both of my kids do it. I design the rollout and presentation of projects at work to make sure my business partners who are using Gen AI view its output skeptically and looking for specific types of flaws. As an avid reader of science fiction over the years, much of which addresses AI as part of society, and worry much less about the power of AI than I do about people who use the output of AI without being critical thinking. It is the kind of following that leads people to enact policies without analysis, and punishes people. And the outcomes are the fault of the people who followed the AI. Because AI has no goals, purpose, or conscience beyond that of its user.