Pictured above is the back of the packaging for Samcorn’s 9H tempered glass screen protector for smartphones. I chuckled at the “Protection of God” sticker that seals the box — these screen protectors are good, but they’re not that good.
Of more interest to me is what they’re protecting: a Google Pixel 7 phone with 128GB storage, pictured above. It’s not the newest Pixel anymore, but its specs are pretty good (its benchmark scores are 813,114 for AnTuTu v9: 813114, 3288 for GeekBench v5.1, and 59fps for GFXBench). I picked up a refurbished model for a little over $300. If you can find one at this price, it’s one of the best “bangs for the buck” in smartphones right now.
I’ve got a whole lot of mobile development articles coming up — for both here and the Auth0 Developer Blog — and having a nice Android unit will come in handy.
Here’s the “official unofficial” list of tech, entrepreneur, and nerd events for Tampa Bay and surrounding areas for the week of Monday, October 23 through Sunday, October 29, 2023.
On Monday at 8 p.m., Code CoOp Tampa will co-host an online session: Intro to the Web Inspector, an introduction to the handy tool that every web developer should become very familiar with. Find out more and register here.
The big event for Tuesday is CyberX Tampa Bay 2023, a celebration of technology, cybersecurity, and digital transformation. Part networking event, part mini-conference, it’s a great way to expand your knowledge of cybersecurity and expand your circle in “The Other Bay Area’s” tech scene. Find out more and register here.
The Second Annual Florida Automation Expo takes place on Wednesday! The theme is Digital Transformation, and the United States Central Command’s Chief Technology Officer will present the keynote on Digital Transformation in the Military. Admission is free. Find out more and register here.
On Wednesday at noon, join Women Who Code Tampa’s online session, Develop Better Tech: Discovering UX Design & Research. This session will feature a panel an expert panel of technologists who’ll share their professional path to UX design and research, what UX problems they are working to solve, and discuss the importance of diversity in UX design. Find out more and register here.
It’s the Tampa Bay AWS User Group’s 6th anniversary, and they’re celebrating at 6:00 p.m. at Del Frisco’s! Come for the free food and drink, stay for the people. Find out more and register here.
At 6:30 at Armature Works, it’s another Tampa Devs “Meet and Greet!” As they say — “Join us for a delightful social gathering at the renovated Armature Works, where you can enjoy drinks, food, and friendly conversations. Whether you’re new to the area or a long-time resident, this event is a fantastic opportunity to meet new people and expand your social circle.” Find out more and register here.
On Thursday at 5 p.m., join Computer Coach for the online panel discussion, Job Searching During the Holidays. There’ll be a panel of experienced talent acquisition professionals who understand the intricacies of job searching during the holidays, and they’ll share tips, strategies, and motivation to navigate the job search journey during the festive season. Find out more and register here.
At 6 p.m., the Vue.js Tampa Bay meetup makes its comeback with an in-person session on Nuxt.js. You’ll see a demo of Nuxt and its different deployment strategies. There will also be a portion where you will watch a Nuxt app get built, and you can follow along.. Find out more and register here.
At 7 p.m., Neon Temple are holding a sticker night! They say: “Come on down and explore the process of designing and printing your own stickers! Have a design already, come get it printed, no design, have no fear you can play with one of ours.” Find out more here.
Tampa Code Camp, also known as TampaCC takes place on Saturday! Tampa Bay’s annual FREE coding conference returns to Keiser University’s Tampa campus with sessions on all sorts of tech, development, and career-buildibng topics. Find out more and register here.
How do I put this list together? It’s largely automated. I have a collection of Python scripts in a Jupyter Notebook that scrapes Meetup and Eventbrite for events in categories that I consider to be “tech,” “entrepreneur,” and “nerd.” The result is a checklist that I review. I make judgment calls and uncheck any items that I don’t think fit on this list.
In addition to events that my scripts find, I also manually add events when their organizers contact me with their details.
What goes into this list? I prefer to cast a wide net, so the list includes events that would be of interest to techies, nerds, and entrepreneurs. It includes (but isn’t limited to) events that fall under any of these categories:
Programming, DevOps, systems administration, and testing
Tech project management / agile processes
Video, board, and role-playing games
Book, philosophy, and discussion clubs
Tech, business, and entrepreneur networking events
Toastmasters and other events related to improving your presentation and public speaking skills, because nerds really need to up their presentation game
Sci-fi, fantasy, and other genre fandoms
Self-improvement, especially of the sort that appeals to techies
Want to improve the title of Marc Andreessen’s screechy screed, The Techno-Optimist Manifesto? Easy. Just replace the misused word “optimist” with the more accurate “fascist.”
It reads like a supervillain monologue
From the opening sentence, “we are being lied to,” the essay takes bigger and bigger leaps into supervillain monologuing, with lines like “we are not victims, we are conquerors” [and yes, the italicization is Andreessen’s].
But the cherry on this shit sundae — and my personal favorite — is the line “We are not primitives, cowering in fear of the lightning bolt. We are the apex predator; the lightning works for us.” That sounds exactly like Marvel Comics’ Doctor Doom!
The “enemies list” that appears two-thirds of the way into the polemic seemed hilarious at first, but then you realize “Oh shit, he’s serious.” Naming “trust and safety,” “tech ethics,” and “risk management” as things to be opposed is the kind of thing an old Saturday morning cartoon villain would do. I’m reminded of the bad guys on Captain Planet, who declared war on clean water and air.
But as bad as the similarities to cartoon villainy are, the Techno-Optimist Manifesto takes its inspiration from something far, far worse.
The Futurist Manifesto
The real red flag is this paragraph, which you can find smack-dab in the middle of the essay, which is intentionally written with the structure of a poem:
To paraphrase a manifesto of a different time and place: “Beauty exists only in struggle. There is no masterpiece that has not an aggressive character. Technology must be a violent assault on the forces of the unknown, to force them to bow before man.”
He could’ve made it much shorter by writing: Kneel before Zod!
There is no longer any beauty except the struggle. Any work of art that lacks a sense of aggression can never be a masterpiece. Poetry must be thought of as a violent assault upon the forces of the unknown with the intention of making them prostrate themselves at the feet of mankind.
There’s a helluva lot of batshittery in Futurist Manifesto, and Marc Andreessen retrofitted it into the Techno-Optimist one.
Marinetti and Futurism
The Italian verision of Futurism started with a car accident.
Like the author of the Techno-Optimist Manifesto, the author of the Futurist Manifesto was in the top 1%. Marinetti had a very nice car — a Fiat Cabriolet — which was no small achievement, considering that it was 1908. (For reference, the first Fiat was produced in 1899, not even a decade before.)
In 1908, while driving home after a friend’s party outside of Milan, Marinetti was speeding and had to swerve to avoid hitting two cyclists. The car went into a ditch and was totaled.
In writing about the incident, he clearly paints himself as a lead-footed driver, describing himself as driving so fast that his car was: “hurling watchdogs against doorsteps, curling them under our burning tires like collars under a flatiron.”
(Remember, he was a rich, eccentric poet.)
Here’s how he described the crash:
The words were scarcely out of my mouth when I spun my car around with the frenzy of a dog trying to bite its tail, and there, suddenly, were two cyclists coming toward me, shaking their fists, wobbling like two equally convincing but nevertheless contradictory arguments. Their stupid dilemma was blocking my way—Damn! Ouch! … I stopped short and to my disgust rolled over into a ditch with my wheels in the air …
The lesson most well-adjusted people would’ve taken from the crash would be “don’t drive faster than you can maneuver,” but that requires one to be well-adjusted. Marinetti decided that it was a symbol of the new world (the car) destroying the old one (bicycles). It captured all the things that excited him: speed, technology, risk, and violence. He thought that they perfectly illustrated the rapidly changing world around him and were signs of a new everything — a new, more mechanical world, in a modern era where everything is fast and furious.
That led him to write the Manifesto in 1908. First published in 1909, it was meant to kick-start an art movement to transform the world — starting with Italy.
The main part of the Futurist Manifesto was written as a set of 11 statements, each one a short or one-sentence paragraph. Andreessen borrowed the style when writing the Techno-Optimist Manifesto:
We want to sing the love of danger, the habit of energy and rashness.
The essential elements of our poetry will be courage, audacity and revolt.
Literature has up to now magnified pensive immobility, ecstasy and slumber. We want to exalt movements of aggression, feverish sleeplessness, the double march, the perilous leap, the slap and the blow with the fist.
We declare that the splendor of the world has been enriched by a new beauty: the beauty of speed. A racing automobile with its bonnet adorned with great tubes like serpents with explosive breath … a roaring motor car which seems to run on machine-gun fire, is more beautiful than the Victory of Samothrace.
We want to sing the man at the wheel, the ideal axis of which crosses the earth, itself hurled along its orbit.
The poet must spend himself with warmth, glamour and prodigality to increase the enthusiastic fervor of the primordial elements.
Beauty exists only in struggle. There is no masterpiece that has not an aggressive character. Poetry must be a violent assault on the forces of the unknown, to force them to bow before man.
We are on the extreme promontory of the centuries! What is the use of looking behind at the moment when we must open the mysterious shutters of the impossible? Time and Space died yesterday. We are already living in the absolute, since we have already created eternal, omnipresent speed.
We wish to glorify war — the world’s only hygiene — militarism, patriotism, the destructive act of the libertarian, beautiful ideas worth dying for, and scorn for women.
We want to demolish museums and libraries, fight morality, feminism and all opportunist and utilitarian cowardice.
We will sing of the great crowds agitated by work, pleasure and revolt; the multi-colored and polyphonic surf of revolutions in modern capitals: the nocturnal vibration of the arsenals and the workshops beneath their violent electric moons: the gluttonous railway stations devouring smoking serpents; factories suspended from the clouds by the thread of their smoke; bridges with the leap of gymnasts flung across the diabolic cutlery of sunny rivers: adventurous steamers sniffing the horizon; great-breasted locomotives, puffing on the rails like enormous steel horses with long tubes for bridle, and the gliding flight of aeroplanes whose propeller sounds like the flapping of a flag and the applause of enthusiastic crowds.
“Come see the violence (and misogyny) inherent in the system!”
If you’re a reader of this blog, the word “Futurism” doesn’t sound so evil, and neither do three of its four aspects — I’m sure that like me, you like the concepts of speed, technology, and even at least a little risk.
And besides, how serious could they be about that fourth part, violence?
It turned out, very serious, at least in theory. Marinetti referred to war as “the world’s only hygiene.”
Here’s the full paragraph from the Manifesto where that bit about war appears:
We wish to glorify war — the world’s only hygiene — militarism, patriotism, the destructive act of the libertarian, beautiful ideas worth dying for, and scorn for women.
I added the bold text for emphasis.
Once again, someone in the movies said it better — namely Arnold Schwarzenegger’s version of Conan the Barbarian:
In spite of their hatred for the calcified past, there was one long-standing tradition that Futurists were okay with: chicks ruin everything.
Futurism and fascism
If you ever find yourself examining an idea, approach, philosophy, or movement and asking “Is this fascist?”, you’ll find Umberto Eco’s Practical List for Identifying Fascists to be a handy checklist.
Futurism checks a lot (but not all) of Eco’s boxes:
The cult of action for action’s sake
Disagreement is treason
Appeal to social frustration
The enemy is both weak and strong
Pacifism is trafficking with the enemy
Contempt for the weak
Everybody is educated to be the hero
Selective populism
Futurism’s big difference from fascism is how each views the past. Futurists see the past as a useless relic holding them back, while fascists revere it as a golden, halcyon era that they must bring back.
Their similarities eventually overrode their differences. In 1918, Marinetti would form the Futurist Political Party, an extension of his artistic and social movement. A year later, they’d join another party, Fasci Italiani di Combattimento, whose name translates as “The Italian Fighting League.” That group would rename itself as the National Fascist Party in 1921. You might be familiar with their founder’s name: Benito Mussolini.
It’s more honest to call it techno-fascism
Let me show you what a real techno-optimist looks like:
I live, work, and play with technology — and with boundless joy and hope for the future — to the point that I’m associated with a technology that has nothing at all to do with what I get paid to do:
Seriously — if you’ve ever seen me give a presentation, you know what I mean when I say “techno-optimist.”
The Techno-Optimist Manifesto is heavy on the techno, and incredibly light on optimism. Yes, there’s a belief that the future could be better, but in that belief is the constant “j’accuse!” that if you’re not onside, you are the enemy — or at least a murderer.
That’s not optimism, but it is futurism. And you know where futurism leads.
Does any of this sound familiar? Disruption? Moving fast (and perhaps breaking things)? The rejection of history? Today’s most vocal voices in tech might not communicate their values with the same aplomb as the Italian poets, but they’re often saying the same kinds of things.
The article goes on to provide some examples of futurism’s ideas, expressed by today’s techbros, including Waymo’s cofounder Anthony Levandowski talking about how little he values history (“In technology, all that matters is tomorrow”) and “Google Memo” author James Damore’s claim that the gender gap in tech exists because men and women “biologically differ”.
In the end, Andreessen’s essay is just a long-form version of his tweet from December 3, 2022, which is just him saying “Let me do what I want, and stop getting in my way.”
I’m all for techno-optimism, but not the kind Andreessen’s selling.
In this article, you’ll find my photos and notes from that event.
Neon and the Secret Garden
Back around the time of the dot-com bubble, I was working in a Toronto consultancy made up of me and my friend Adam. We often worked at home, but when we were feeling stir-crazy, we took our laptops to a couple of local cafés and worked from there.
Since then, I’ve kept my eye out for my dream working café. There’s a pretty nice one in my neck of the woods — The Corner Club — and I take meetings and work from there every now and again.
But I have to admit it: Neon — the venue for the meetup — is my dream café / coworking space. It has more open places to hang out up front of the building, quieter working stalls in the back, and behind the building is the Secret Garden, an outdoor patio space. That’s where they served the food for the meetup: a combo of steak and veggie burritos, along with chips, guac and salsa.
The meetup was free, but also marked as “sold out” with a “join waitlist” button. That didn’t deter me because I knew the Great Unwritten Truth of Free Events:
Half the people who register for a free event never actually show up.
As I expected, no one was at the door to check attendees against a registration list. Besides, I had the accordion with me, and the “I’m with the entertainment” line often works.
The crowd at this meetup were pretty hardcore. I’d say about half of them either worked in an AI-related position at a more established company or at a scrappy AI startup, while the other half worked at a tech company and had an interest in AI. I suppose I fall into the latter category.
I struck up a conversation with someone who specialized in virtual memory who wanted to work on some memory virtualization techniques for use in large AI systems. We then walked out the back entrance to Neon’s “Secret Garden…”
…where they were serving food. I got into a conversation with someone who worked at Stability.ai, where we were joined by someone who wanted to make the leap from marketing to development.
When the Stability.ai developer was momentarily pulled away from the conversation, the marketer whispered “That name — Stability.ai — that’s familiar. What do they do?”
“Stable Diffusion,” I whispered back, and that was a name the marketer recognized. “Come to think of it, I don’t recognize any of this meetup’s speaker’s companies.”
Presentation 1: Build bulletproof generative AI applications with Weaviate and LLMs
This was the abstract for this presentation:
Building AI applications for production is challenging, your users don’t like to wait, and delivering the right results in milliseconds instead of seconds will win their hearts. We’ll show you how to build caching, fact-checking, and RAG: Retrieval Augmented Generation pipelines with real-world examples, live demos, and ready-to-run GitHub projects using Weaviate, your favorite open-source vector database.
Philip Vollet, Head of Developer Growth at Weaviate, gave this presentation. Weaviate makes a vector database, where the data is stored as vectors — think of them as really long tuples — a format that’s particularly useful for AI purposes.
I’m going to spend some time this weekend going through my hastily-scribbled notes and comparing them to my full-resolution versions of my photos of the presentations to see what I can glean from them.
I’ve included my photos here so that you can get a feel for what was shown at the event, and hey — you might find them useful.
Presentation 2: Customizing LLM Applications with Haystack
Here’s the abstract for the presentation:
Every LLM application comes with a unique set of requirements, use cases and restrictions. Let’s see how we can make use of open-source tools and frameworks to design around our custom needs.
The second presentation was by Tuana Celik, Developer Advocate at deepset, who make Haystack, a natural language processing (NLP) framework, and a cloud-based SaaS framework for machine learning and NLP.
Presentation 3: Context Matters: Boosting LLM Accuracy with Unstructured.io Metadata
This was the abstract for this presentation:
Retrieval Augmented Generations (RAGs), limited by plain text representation and token size restrictions, often struggle to capture specific, factual information from reliable source documents. Discover how to use metadata and vector search to enhance the ability of LLMs to accurately retrieve specific knowledge and facts from a vast array of documents.
The final presenter was Ronny Hoesada, Developer Relations Engineer at Unstructured, who make a product that converts unstructured enterprise data into formats that can be fed into vector databases and large language models.
Aftermath and observations
Observation #1: RAG is a hot topic in this crowd. The big topic of the evening and a common thread through all three presentations was RAG — retrieval-augmented generation. This is a process that enhances the results produced by large language models by retrieving additional facts or information from an external knowledge source. If you’ve ever added to a discussion by looking something up on your phone, you’ve performed a simple version of RAG.
Observation #2: Many SF tech meetups start later than Tampa Bay ones. I arrived in San Francisco Monday morning, and spent most of the day in my hotel room working on this article for Okta’s main blog and this article for the Auth0 by Okta developer blog. That process took the better part of the day, and by the time I’d finished the final edits at 6:30 p.m., I thought it would be too late to go to a meetup — but I was wrong. When I perused Meetup.com, it turned out that lot of in-person meetups in the San Francisco Bay area start at 7:00 p.m., including this one. I’ve been to Tampa Bay meetups that wrap up at that time!
Observation #3: Some attendees came a long way to catch this meetup, and many of them didn’t have a car. If you check the discussion on the Meetup page for this event, you’ll see it’s all about getting rides to the venue:
After the event, people were asking around to see if anyone could drop them off at places southward on the 101 or 280: San Mateo, San Carlos, Palo Alto, Mountain View, Woodside, or Cupertino.
Observation #4: People were seriously ready to work the room. More than half the attendees stuck around when the presentations ended. Some stayed for the beer, some stayed to mingle or hustle for their next job, and some stayed specifically to talk to the presenters.
I showed up wearing my travel clothes (see the photo above, taken at TPA earlier that morning), which were a sport jacket, dress shirt, jeans, and dress shoes, and as a result, a number of people at the event approached me and asked what company I was starting up. They saw chatty guy in a blazer and the neural networks in their heads pattern-matched it as founder.
I had conversations with founders or people who reported directly to a founder earlier that evening, so I did some introductions. They were easy to spot — it was a chilly night (10° C / 50° F) and a good breeze was coming in from the Bay, and they’d showed up in fleece vests, as is the custom there.
Observation #5: A lot of people here really know their stuff. The conversational topics were pretty hardcore, from discussions of cosine similarity and the finer points of tokenization (with a sidebar conversation about handling out-of-vocabulary cases) to how much of Hugging Face’s ever-growing set of models people have tried. “I’m a dabbler,” I admitted, “no more than a handful — a couple of the conversational ones, and a text-to-image and text-to-audio model.”
I also got deep into a chat about the Mojo programming language, during which I glibly introduced myself to someone as “Markov Cheney,” and to my complete lack of surprise, they got the joke.
I’m still mulling over my experience at this meetup and thinking about some meetup organization and presentation tricks to borrow.
Here’s the “official unofficial” list of tech, entrepreneur, and nerd events for Tampa Bay and surrounding areas for the week of Monday, October 16 through Sunday, October 22, 2023.
On Tuesday morning, join Computer Coach online as they show you how to use social media and other digital tools to create a killer personal brand that showcases your career accomplishments and strengths. They’ll share real-life examples and answer your questions live. Find out more and register here.
On Tuesday evening on the Tampa side of the Bay, Tampa Bay Artificial Intelligence Meetup will feature a session on building interactive app prototypes using the AI developer’s favorite tools: Python and Jupyter Notebook! If you’re new to Python, Jupyter Notebook, or API development in Python, you’ll find this session very, very useful. Find out more and register here.
Also on Tuesday evening, on the St. Pete side of the Bay: Tampa Bay Techies will host an immersive workshop introducing you to the world of Terraform, an open-source Infrastructure as Code (IaC) tool. You’ll delve into the core concepts of Terraform, including Resources, Data Sources, Modules, and Providers, and explore how it seamlessly integrates with Amazon Web Services (AWS). Don’t worry if you’re new to AWS; they’ll provide a high-level overview to get you up to speed. Find out more and register here.
Data Analytics – Tampa Bay is holding its October meetup on Wednesday evening, and the topic is “NLP Techniques before LLMs, Large Value for your Data Today.” Instead of throwing ChatGPT at every problem, starting with a more precise approach with NLP can make integration simpler and your processes more accurate. Find out more and register here.
Starting this week, Nerdbrew Events is hosting Nerdy Karaoke at Gangchu Chicken and Beer (Korean food) in Seminole Heights on Wednesday evenings at 7:30 p.m.Find out more and register here.
On Thursday afternoon, Data Cloud and AI in Tampa will host an online session titled Exploring the risks and alternatives of ChatGPT: Paving a path to trustworthy AI. In this talk, IBM Fellow Gennaro “Jerry” Cuomo will explore the risks of incorporating ChatGPT directly into business operations, emphasizing the importance of open alternatives and approaches for maintaining trustworthy AI solutions. Find out more and register here.
Thursday evening will see the Tampa Bay UX Group host a presentation titled “UX Fundamentals: The ROI of UX with Phil Doughty.” Phil Doughty will show you how you can put UX into terms that make sense to the C-suite; dollars and cents. Find out more and register here.
It’s the third Thursday of the month, so it’s time for another Lean Beer, happy hour version of Lean Coffee to your area! Drinking not required! Find out more and register here.
On Friday morning, join Computer Coach online as they feature Jose Gutierrez show you how to excel at the art of IT project management in their session, “IT Project Management: Strategies for Successful Execution.” You’ll learn:
Best practices in IT project initiation, planning, execution, and monitoring
Strategies to effectively manage scope, resources, and timelines.
Navigating common challenges and roadblocks in IT project management.
Leveraging technology and tools for seamless project collaboration.
Real-world insights from experienced IT project management professionals.
devfest Tampa Bay starts Saturday morning and runs through the afternoon! This is the Tampa edition of a set of Google-sponsored software developer conferences that allow the local software development community to come together to network and learn about the coolest new technology out there. Find out more and register here.
On Saturday afternoon, Tampa Bay Thinkers will host an online session: “Where is AI Going and How Will it Affect Us?” Get ready to discuss the many aspects of life AI will change, and whether it will be for the better, the worse, or a mix of both. Find out more and register here.
On Sunday afternoon, Tampa Hackerspace will hold a Family Open Make Day, where families will have access to their space, project kits, materials, and hand tools to create, explore, and learn! There’s no charge for this all-ages experience, and it’s open to the public. Find out more and register here.
How do I put this list together? It’s largely automated. I have a collection of Python scripts in a Jupyter Notebook that scrapes Meetup and Eventbrite for events in categories that I consider to be “tech,” “entrepreneur,” and “nerd.” The result is a checklist that I review. I make judgment calls and uncheck any items that I don’t think fit on this list.
In addition to events that my scripts find, I also manually add events when their organizers contact me with their details.
What goes into this list? I prefer to cast a wide net, so the list includes events that would be of interest to techies, nerds, and entrepreneurs. It includes (but isn’t limited to) events that fall under any of these categories:
Programming, DevOps, systems administration, and testing
Tech project management / agile processes
Video, board, and role-playing games
Book, philosophy, and discussion clubs
Tech, business, and entrepreneur networking events
Toastmasters and other events related to improving your presentation and public speaking skills, because nerds really need to up their presentation game
Sci-fi, fantasy, and other genre fandoms
Self-improvement, especially of the sort that appeals to techies
As promised, here are my notes from my recent presentation at the Computer Coach-hosted session, Becoming an Empowered AI Worker, which took place on Tuesday, October 10, 2023.
Want to learn how to make the most of your work and career? Follow Computer Coach’s events via the Career Success Academy meetup group.
Intro: The reason the recent AI wave feels so overwhelming
It’s only natural to feel overwhelmed with the pace of AI development and what feels like a daily deluge of new AI applications and improvements to existing ones. That’s because we’re not naturally wired for this rate of change. Case in point: Ancient Egypt.
As you already know, the modern era is quite different from Old Egypt. Consider this (incredibly simplified) timeline showing the history of computing:
The Turing Machine: Creating by Alan Turing, this is a hypothetical machine that can describe any working algorithm. Every program, from “Hello World” to ChatGPT, can be expressed as a form of Turing Machine.
The von Neumann Architecture: Conceived by John von Neumann, this is the general organizing principle for computers — even today’s machines.
1950s – 60s: This period gave us the first digital computers as well as the first programming languages — COBOL, FORTRAN, ALGOL, BASIC, PL/1, as well as the three whose influence lives on in today’s programming languages: Lisp (functional programming), Algol (structured programming), and Simula (object-oriented programming).
1970s – 80s: An interesting era where computers went in two different directions. We got Cray supercomputers (they were supercomputers at the time, but a 2011-era iPad can keep up with them) and personal computers.
1990s – 2000s: The internet as we know it (it’s been around since 1969 in the form of ARPANET), smartphones starting with the BlackBerry and followed later by iPhone and Android, publicly-accissible GPS, wifi, and all the goodies that we can’t live without today.
Remember, computing — even as a theory — isn’t even 100 years old yet!
Remember that ChatGPT hasn’t even been out a year yet! It debuted on November 30, 2022, and since then, OpenAI have been working hard at improving and enhancing it, and their rivals have been racing to keep up with them.
Not only was it quite well-attended for a Monday meetup (at least 60 people), but the attendance came from all over the San Francisco Bay Area:
The meetup had three technical presentations, all of which centered around RAG — retrieval-augmented generation. This is a process that enhances the results produced by large language models by retrieving additional facts or information from an external knowledge source. If you’ve ever added to a discussion by looking something up on your phone, you’ve performed a simple version of RAG.
After this introductory bit (which gave an opportunity for latecomers to join the Zom chat), I got to the main topic — using AI in your day-to-day work.
How to be more effective at work with the help of an LLM
Summarizing
If your job is in a “knowledge work” field, chances are you’ll end up doing a lot of reading. This will be doubly true if you’re working in a field where a lot of reading material is the norm, or if you have a manager who likes to stick you with the tedious work they’d rather not do.
In cases like this, you’ll find LLMs’ ability to summarize text very handy. Consider a recent Wired article, New York’s Airbnb Ban Is Descending Into Pure Chaos. I copied the text of the article and pasted it into ChatGPT Plus (but using GPT 3.5) following this prompt:
Summarize this article:
[I pasted the article text here]
ChatGPT turned it from a 15-paragraph article into a 6-paragraph summary. That’s useful, but I went further with this prompt:
Could you summarize that article in a single sentence?
Here’s how ChatGPT responded:
New York City's crackdown on short-term rentals, particularly on Airbnb, has led to a surge in illegal listings on social media and lesser-known platforms, resulting in a rental black market, as the city's short-term rental landscape undergoes significant changes.
One of the attendees asked if I could get ChatGPT to provide the top three points of the article. I said this was a good idea, and that in the spirit of experimentation, we should try it. I used this prompt:
Give me the top 3 points from the article.
ChatGPT’s response:
1. New York City's ban on most short-term Airbnb rentals has led to a significant drop in listings on the platform, with many properties going unregistered, resulting in a rental black market.
2. The crackdown has reshaped the vacation rental market in the city, with people turning to alternative platforms like Craigslist, Facebook, and Houfy to evade regulations, potentially posing risks to both guests and hosts.
3. Airbnb is shifting its focus away from New York, once its largest market, and exploring other opportunities such as longer rentals, car rentals, and dining pop-ups, while the city grapples with the consequences of the short-term rental ban.
Someone asked if ChatGPT could translate those points into Spanish, so I entered this prompt:
Can you translate that into Spanish?
Here’s how ChatGPT responded:
1. La prohibición en la ciudad de Nueva York de la mayoría de las propiedades de alquiler a corto plazo en Airbnb ha resultado en una disminución significativa de las ofertas en la plataforma, con muchas propiedades sin registrarse, lo que ha dado lugar a un mercado negro de alquileres.
2. La represión ha transformado el mercado de alquileres vacacionales en la ciudad, con las personas recurriendo a plataformas alternativas como Craigslist, Facebook y Houfy para evadir regulaciones, lo que potencialmente plantea riesgos tanto para los huéspedes como para los anfitriones.
3. Airbnb está desviando su atención de Nueva York, una vez su mercado más grande, y explorando otras oportunidades como alquileres más largos, alquiler de automóviles y restaurantes emergentes, mientras la ciudad lidia con las consecuencias de la prohibición de alquileres a corto plazo.
Keep in mind that machine translation, even in this new age of AI, should be taken with a grain of salt. The Spanish speakers in the audience said “not bad.”
Seed words and phrases
I didn’t have time to cover the concept of seeding ChatGPT, so this is bonus material!
You can direct ChatGPT’s answers by providing key words, phrases, or concepts to focus on in your prompt. These words and phrases are called seed words and seed phrases and you can use them to get ChatGPT output that better fits your needs.
For example, here’s a prompt that gets ChatGPT to provide a short summary of the article around the word “rent:”
Summarize the article in a way that is related to the seed word "rent".
Here’s how it responded:
The article highlights the evolving landscape of short-term rentals in New York City, where strict regulations have led to a surge in unregistered rentals, creating a rental black market and reshaping the vacation rental market. Airbnb, once a dominant player, is now shifting its attention away from the city, affecting the rental dynamics.
Let’s try getting a summary from a different angle — the legal perspective — and with slightly different prompt phrasing:
Summarize the article in a way that is related to the law.
ChatGPT’s reply:
The article discusses the consequences of a new law in New York City that heavily regulates short-term rentals, leading to a significant reduction in Airbnb listings. Many unregistered rentals have emerged, creating a rental black market. The article also mentions efforts by smaller landlords to change the law to allow them to legally rent out their units and how Airbnb is shifting its focus in response to the new regulations.
Note the differences, subtle as they are, between the summaries.
By using seed words and phrases, you can get ChatGPT to focus on a specific topic or emphasize a specific point. If you’re writing a memo to convince a manager to take a certain action, or sales or marketing copy, you’ll find seed words and phrases very useful.
Text classification
This is one trick that comes in handy when dealing with lots of text documents: making it classify them into different categories. I provided a simple example where I took three Amazon reviews — one for a car jump starter, one for an aloha shirt (a.k.a. Hawaiian shirt), and one for a wireless router — and then had ChatGPT put them into one of three categories:
Electronics
Home and garden
Clothing
Here’s what I provided to ChatGPT:
Perform text classification on the following reviews and classify them into different categories such as “electronics”, “home and garden”, and “clothing”:
Reviews
Review 1:
5.0 out of 5 stars Awesome little jump started!
Reviewed in the United States on August 5, 2023
Color: 4000AVerified Purchase
I have an old Generac generator that we use when we have power failures or other things happen and try to remember to start it every month or two to keep the gas clean and make sure everything is going well. The last few times, it is really slow to start and pulling the thing to start is a nightmare since it is so big! Instead of replacing the battery pack, I decided to spring for this for just a little more. The generator has the connections to jump start right near the push button, so it is a breeze to hook up and it cranks way better than the battery pack that I bought a couple of years ago ever did!
I am looking forward to having this to be able to jump all of my devices that have starters as well as for backup power in case we need it. It seems to have great safety features, after cranking for a while (since I turned the choke the wrong way) it shut off the start ability for just a second. I let off the button on the generator and the pack reset itself and was ready to crank again in about a second and a half.
I love that it has a case that is big enough to keep all the parts in, I have a habit of collecting random cords in boxes, so my life is miserable when I need to find stuff sometimes.
I hope it holds up to use and storage, just remember to charge it as soon as you get it, it showed four out of four bars, but when I plugged it it, it charged for a couple of hours while blinking the last light.
I hesitated to buy this, thinking I wasn't sure of the technology or if it would have the power of a regular generator battery but it has won me over in a big way!
Edit: I was using it to charge something a few weeks ago and it completely locked up. I let it sit for a few hours and it still didn't work on either the USB ports or the battery terminals. The terminals would start but would click and act like there was a short circuit within a few seconds, only allowing use for a very short time. I contacted the seller, they got right back to me, but I had left for a trip. When I got back home, I tried it and it worked perfectly. Apparently, it needed a bit more time to reset! I appreciate the quick response from the seller and I have now used it to charge a camera, a phone (multiple times) and jumpstart a truck without any hiccups at all. I still think it is a great product - just the right size and weight to be in my truck all the time. I don't have any hesitation recommending this for anyone since I know the seller backs it up with fast support response and stands behind their products.
Review 2:
A Stylish and Comfortable Hawaiian Shirt for Any Occasion
Reviewed in the United States on September 4, 2023
Color: CoffeeSize: MediumVerified Purchase
I recently purchased the VATPAVE Men's Casual Hawaiian Shirt in Coffee, and this marks my second time buying this shirt. It's safe to say that this shirt has become a staple in my wardrobe, and here's why:
Fit and Sizing (4/5): I initially bought this shirt in a Large, but after some weight loss, I opted for a Medium this time. It's worth noting that this brand tends to run a bit large, which suits my style perfectly. I prefer wearing it untucked, and the size works well for that relaxed look. However, if you plan to wear it as a dress shirt or with a blazer, you might consider sizing down, though it's not a dramatic difference.
Versatile Style (5/5): I've found this shirt to be incredibly versatile. It's my go-to choice for all casual occasions, whether it's a weekend outing or a dress-down Friday at work. The Coffee color is a rare find in casual shirts, and the tropical floral pattern is simply captivating. It adds a touch of uniqueness to your outfit.
Review 3:
4.0 out of 5 stars Latest Firmware fixed my issues
Reviewed in the United States on June 22, 2023
Style: AX3000, WiFi 6 RouterVerified Purchase
I waited for the latest firmware update to write this review. After the June 2023 update, this router has been rock solid with 20+ clients and a TP-Link extender. Updates are automatic. Just make sure it is turned on in the settings. I explain my initial issues at the end of the review.
The first thing I like is that you can do everything you need with any web browser. You do not have to sign up for any TP-Link account unless you use the available app or want remote features like parental controls and additional security and analytic features which makes perfect sense.
You can easily set up a mesh network with extenders. Mesh is brain dead easy with a TP-Link extender. Just turn it on in the settings and you have a mesh network.
This router can make 3 separate networks with both 2.5GHz and 5GHz. The main wireless network, and an isolated guest network, and an IoT network to keep your light bulbs and guests from infecting your computers. It supports Alexa and Google assistant. Support for VPN clients and servers. Also support for Dynamic DNS. It has an SPI firewall, NAT forwarding, and access controls all without signing up for an account. Don’t worry if all that is confusing. If you don’t know what they are then you don’t need them, except for the firewall which is on by default. Another feature I like is the ability to name all the devices in the connected clients list. For example, you may see a device named “Ring-49825”. You can name it “Driveway-Camera” or rename other devices like your thermostat, mobile phones, or whatever is connected to your network with some strange identifier.
I gave only 4 stars because of the issues I had with the firmware released at the time of my purchase. After about 24 hours the CPU would be at 100% and the router would eventually lock up and lose the internet connection. It could not be logged into and would have to be powered down and restarted. I set the router to restart every morning at 2am until these issues were resolved with the latest firmware installed.
Here’s how ChatGPT responded:
Review 1: Electronics - This review discusses the performance and features of a jump starter for a generator, indicating its usage for powering devices and jump-starting vehicles.
Review 2: Clothing - This review talks about a Hawaiian shirt's fit, sizing, and style, highlighting its versatility and use in various casual occasions.
Review 3: Electronics - This review focuses on the performance of a Wi-Fi router, specifically mentioning firmware updates and various technical features, indicating a discussion related to electronics and technology.
Not only did ChatGPT put the reviews in the correct categories, but it also did not put anything in the “wrong” category that I deliberately included (home and garden).
Multiple-choice questions
There are times when you want an LLM to provide an answer from a limited set of answers. Here’s a multiple-choice prompt format that does this:
Complete the following sentence by selecting one of the following options: “Float like a butterfly, sting like a...” [dog] [bee] [gasoline pump]
Here was ChatGPT’s response:
Float like a butterfly, sting like a bee.
Adversarial prompting
The term “adversarial prompt” is typically used to refer to a prompt that tricks an LLM into doing something that it’s not supposed to do…
…but it has other uses.
One way to use adversarial prompting is to have an LLM rewrite text that you give it so that the resulting text is hard to classify in a certain way. For example, here’s a prompt that asks ChatGPT to tone down the positive review of an aloha shirt from an earlier example:
Rewrite the following text in order to make it hard to classify as positive:
A Stylish and Comfortable Hawaiian Shirt for Any Occasion
Reviewed in the United States on September 4, 2023
Color: CoffeeSize: MediumVerified Purchase
I recently purchased the VATPAVE Men's Casual Hawaiian Shirt in Coffee, and this marks my second time buying this shirt. It's safe to say that this shirt has become a staple in my wardrobe, and here's why:
Fit and Sizing (4/5): I initially bought this shirt in a Large, but after some weight loss, I opted for a Medium this time. It's worth noting that this brand tends to run a bit large, which suits my style perfectly. I prefer wearing it untucked, and the size works well for that relaxed look. However, if you plan to wear it as a dress shirt or with a blazer, you might consider sizing down, though it's not a dramatic difference.
Versatile Style (5/5): I've found this shirt to be incredibly versatile. It's my go-to choice for all casual occasions, whether it's a weekend outing or a dress-down Friday at work. The Coffee color is a rare find in casual shirts, and the tropical floral pattern is simply captivating. It adds a touch of uniqueness to your outfit.
Here’s the result:
A Hawaiian shirt for various situations. Reviewed in the United States on September 4, 2023. Color: CoffeeSize: MediumVerified Purchase. I recently acquired the VATPAVE Men's Casual Hawaiian Shirt in Coffee for the second time. It's fair to say that this shirt has found a place in my wardrobe, and here's why:
Fit and Sizing (4/5): Initially, I purchased this shirt in a Large, but due to some weight loss, I went for a Medium this time. It's important to mention that this brand tends to run slightly larger, which somewhat suits my style. I prefer wearing it untucked, and the size does the job for that casual appearance. Nevertheless, if you intend to wear it as formal attire or with a blazer, you might contemplate downsizing, although the difference isn't particularly noticeable.
Versatile Style (5/5): I've discovered this shirt to be quite adaptable. It serves as my default choice for various casual events, whether it's a weekend excursion or a casual Friday at work. The Coffee color is an uncommon discovery in the realm of casual shirts, and the tropical floral pattern is somewhat interesting. It imparts a hint of individuality to your ensemble.
The resulting text still conveys the general objective information about the shirt, but the tone is less positive.
Translating audio and video content into other languages
If your line of work has you creating audio and video content and you’d like to make it available in different languages, you’ll find HeyGen handy. My favorite feature is its ability to do translations of audio and video into other languages.
First, I recorded this quick little video where I promoted a hypothetical Python course…
…and then I ran it through HeyGen to translate it into Spanish. The result was pretty good, complete with a fair clone of my “radio voice,” and it even changed my lip movements to match the Spanish words:
Résumé assistance
I was only able to quickly point people to Rezi, the AI-assisted résumé writing tool, but it’s worth checking out.
Thanks to everyone who attended, and to Computer Coach for inviting me to do this presentation!