It had been a while since I built a Steampipe plugin using LLMs, which have since evolved, so I decided to team up with my assistants and tackle another item on my wishlist: a plugin to enable SQL queries of the WordPress API. Of course, a Steampipe plugin doesn’t really come to life until its foreign tables power a set Powerpipe dashboards. Here’s one of them, for a selected The New Stack author. That’s the end result, but let’s unpack how I got there.
Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile
Articles by BYTE Magazine's..
How LLMs Guide Us to a Happy Path for Configuration and Coding
We all have different learning styles. Mine, sadly, involves trying all the wrong ways to do a thing before I finally arrive at the right thing. This is not always bad. You can learn a lot about a complex system by exploring all of the unhappy paths, and that learning can be valuable. But often you just want to walk the happy path and proceed as quickly as possible to a destination. As our systems grow ever more complex, layered and interdependent, unhappy paths multiply.
Choosing When To Use (or Not Use) LLMs as a Developer
“My daughter will never know what it’s like to be lost.” I forget who said that about 10 years ago, but the message sank in and resonates more deeply as we are ever more profoundly augmented by tech. The speaker was referring, of course, to the fact that almost nobody younger than 15 (now 25) is ever without the handheld GPS wayfinding device that we anachronistically call a phone.
Human Insight + LLM Grunt Work = Creative Publishing Solution
If you publish product documentation to a website, this might be a familiar pattern. You write an initial draft in Google Docs so your team can review and propose changes. It’s a rich authoring environment in which you can insert images by pasting bits copied from screens, and easily create and rearrange tables. When the team reaches a consensus, you have a nice representation of the web page you’d like to appear on your site. But how do you make that happen?
Techniques for Using LLMs to Help Write a Postgres Function
In this post, we’ll walk through a real-world example of using ChatGPT to iteratively develop a Postgres function that suppresses the display of duplicate primary columns. Along the way, we’ll explore useful SQL concepts like window functions and SETOF JSON (from Postgres), and we’ll see how an AI assistant can help you learn in moments of need. Soon after I started building dashboards to keep track of my Pipes resources, I ran into a familiar challenge.
How LLMs Can Unite Analog Event Promotion and Digital Calendars
How LLMs Can Unite Analog Event Promotion and Digital Calendars tutorial, Photo by Yonghyun Lee on Unsplash. When I worked on community calendar aggregation, I didn’t just want to solve what remains an unsolved problem. I also wanted to teach communities how to think computationally. “Let’s teach everyone to code” had become a mantra. For some of us, that meant acquainting nontechnical people with key ideas — from information science and software construction — that we saw as useful to everyone.
The Future of SQL: Conversational Hands-on Problem Solving
If you’re returning to SQL after a long absence, as I did a few years back, there are important changes to know about. First, JSON. Many SQL-oriented databases now support JSON columns for arbitrary tree-structured data. Second, common table expressions (CTEs) that you can use to express a complex query as a pipeline of steps that are simple to understand and verify.
Code in Context: How AI Can Help Improve Our Documentation
Although I’ve written a few Steampipe plugins, they’ve only required a basic understanding of the plugin SDK. I’m surely not the only one who has struggled to grasp its more advanced mechanisms. At our annual company hackathon in 2022, I participated in a weeklong sprint to improve the SDK’s documentation, working with several team members including Steampipe’s lead developer (who is the author of the SDK).
Using AI to Improve Bad Business Writing
I once taught expository writing and have long felt that software tools ought to be able to help people learn how to write more clearly and effectively. In a previous post I applied core principles — omit needless words, use active voice, avoid jargon and cliche, cite specific examples — to a typical badly-written press release.
Creating a GPT Assistant That Writes Pipeline Tests
Photo by JJ Ying on Unsplash VOXPOP Try our new 5 second poll. It's fast. And it's fun! Why Will You Get Laid Off? What is the most likely reason your employer will consider laying you off in 2024?
How to Learn Unfamiliar Software Tools with ChatGPT
I regret never having studied calculus in school, and over the years I’ve made a few efforts to fill in that gap in my knowledge. It would have been a different story, I’m sure, if I’d been lucky enough to have Eddie Woo as a math teacher; it’s amazing to have his classes available on demand. I’ve also learned from Sal Khan’s videos, and this time around I went back to Khan Academy to see how its integration of ChatGPT changes the learning experience.
Learn by Doing: How LLMs Should Reshape Education
Today my friend Greg Wilson, who was translating a tidyverse/Pandas idiom to SQL, asked me the following question: OK, what’s wrong with my SQL?
7 Guiding Principles for Working with LLMs
In Seven ways to think like the web, I codified a set of patterns that emerged from my experience as a web-first writer and software developer. The idea was (and is) that the web’s architecture — described by Roy Fielding as an internet-scale distributed hypermedia system — exhibits a grain that you want to align with.
Puzzling over the Postgres Query Planner with LLMs
VOXPOP Try our new 5 second poll. It's fast. And it's fun! What news from AWS re:Invent last week will have the most impact on you? Amazon Q, an AI chatbot for explaining how AWS works. Super-fast S3 Express storage. New Graviton 4 processor instances. Emily Freeman leaving AWS. I don't use AWS, so none of this will affect me. We'd love to hear what you think. Steampipe plugins read APIs into Postgres foreign tables.
Techniques for Using LLMs to Improve SQL Queries
The problematic query was supposed to detect Azure virtual machines whose network security groups allowed inbound access on sensitive ports. A user reported that for two different test cases the query reported OK when it should have reported Alarm. In the first case the security group was attached directly to the VM’s network interface; in the second it was attached to the VM’s subnet.
Let's Talk: Conversational Software Development
Here’s the prompt that kicked off what turned into a very successful interaction with ChatGPT. I’ll give you a test script and the output it is testing, and ask about strategies to improve the test, OK? Here’s the script.
How to Use LLMs for Dynamic Documentation
The other day I revisited a SQL query I’d written a while ago, in order to adapt it to the latest version of the GitHub plugin. The minor adjustments took longer than they should have. Why? I’d forgotten how the query works! And of course, I hadn’t written any comments; it seemed simple at the time, right? Here’s the original query. It reports recent commits for a set of Steampipe plugins.
How LLMs Helped Me Build an ODBC Plugin for Steampipe
I’d written my first two Steampipe plugins (Hypothesis, Mastodon) in the pre-LLM era, so I was eager to work with my team of assistants on my next project: a plugin for ODBC (Open Database Connectivity). Steampipe nominally maps APIs to database tables. When you select * from aws_sns_topic, Steampipe winds up calling the AWS ListTopics API. Many Steampipe plugins work like that: a table corresponds to a specific API call. But some plugins work in a more general way.
Learning While Coding: How LLMs Teach You Implicitly
I’ve always been a hands-on learner, especially when it comes to learning how to use — and create — software. I wish I could learn protocols from specifications, come up to speed with apps by reading documentation, and absorb coding techniques from structured lessons, but things don’t come alive for me until I’m enmeshed in a project, focused on a tangible goal, and able to run live code in a debugger. In Radical just-in-time learning, I recalled my favorite scene in The Matrix.
Test-Driven Development with LLMs: Never Trust, Always Verify
As community lead for Steampipe, I’d long wanted a better way to visualize project activity. Since I joined about two years ago, the suite of plugins has grown from 42 to 136, and existing plugins are constantly updated with new tables, enhancements, and bug fixes. All these updates appear in a community Slack channel and on social media, but I’d been wanting an automatic summary of the changes on a monthly or quarterly basis.
Should LLMs Write Marketing Copy?
On The Marketing Mix podcast, Charley Karpiuk advises against using LLMs to write marketing copy, and he proposes an interesting rule: Machines should write for machines — e.g. by creating metadata — and people should write for people. That sounded like good advice, and I resolved to follow it, but in the thick of the website makeover discussed last time, I found myself bending the rule.
How Large Language Models Assisted a Website Makeover
A major project for me in these past few weeks has been a website makeover that combines two pre-existing sites and adds new marketing literature. I’ve used my team of Large Language Model (LLM) virtual assistants to help with both coding and writing tasks. I’ll discuss coding here, and how the assistants helped with the writing of prose next time. Standardizing Titles One of the legacy sites used title-case: capitalize most words, excluding words like “a,” “an,” “the,” “but” and proper nouns.
Elevating the Conversation with LLM Assistants
Here is some CSV data that created a problem for Steampipe’s CSV plugin. Can you see what’s wrong? Last week several of us failed to see, at first glance, what was wrong. Excel was happy with the data, and so was a CSV validator, but when Steampipe loaded it by way of the CSV plugin the headers got mangled.
Using LLM-Assisted Coding to Write a Custom Template Function
In this series of articles I’ll explore LLM-assisted coding through a particular lens: my own experience as an average developer, working in and around an open source codebase, chronicling the ways in which LLM assistants do (or don’t!) make me better at various tasks. I’ve been coding for decades, more as a toolsmith than a production developer; tasks in my lane have typically been feature prototypes, automation scripts, data analysis, document processing.
Show More
loading
Actions
Is this you?
As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.Get in touch with BYTE
Contact BYTE, search articles and posts on X, monitor coverage, and track replies from one place.
Learn more about Muck Rack