Thanks for visiting! You'll find a bunch of musings I've been writing around these parts since the early 2000's.
Lately, I've been reviewing a lot of books.
But I also write about code and my experiments using generative AI.
But really, you're just here to see pictures of Benson.
Awhile back, I was fortunate enough to be invited to a semi-weekly “build night.” It’s a casual gathering where a bunch of random folks hack on all sorts of things: software, hardware, AI tooling, art. It is awesome! There are some seriously inspiring people there.
One longtime attendee showed off a project involving 3D-printed tiki sculptures lit from within by LEDs. Each sculpture had an ESP32 inside, controlling the LEDs and communicating via Bluetooth LE. A scroll wheel controller mounted on top could change the brightness and pattern, and the effects would sync across all the sculptures. It was ridiculously cool!
I happened to randomly have an ESP32 dev kit sitting inside a box of random electronics in my garage. I ordered a few more (these things are ridiculously cheap) and decided to experiment. Despite not having touched ESP32s before, it felt like a fun challenge.
Ultimately, I ended up cutting off a few LEDs from a WS2812 LED strip, soldering some wires up to the necessary connectors and then plugged them into a breadboard.
After snipping a few LEDs off a WS2812 strip and wiring them up to a breadboard, I used VS Code and the PlatformIO extension to vibe-code a basic Bluetooth host and client (shout-out to Claude for the help!).
The result?
The host ESP32 registers itself as a Bluetooth service using a UUID, loops through a series of colors, and broadcasts the current color value.
The client ESP32 scans for that UUID. If it finds it, it listens for the color data and updates its own LED. If not, it pulses red with a slow “heartbeat” to signal it’s waiting.
You can see it in action, below. Pretty wild! It starts off with the host disconnected. The only communication between the two is via Bluetooth.
It’s ability to generate images and render text according to your exact prompt is incredible. We can now have full on automated AI memebots.
A four panel cartoon strip
first panel: a software engineer sitting in front of a computer screen on a Zoom meeting
second panel: the software engineer tells the participants (with a speech bubble): “I’m telling you, AI is coming for our jobs!”
third panel: we just see a slight closeup of the software engineer (the computer monitor isn’t visible)
fourth panel: same as the first panel except all the participants are now robots
Same angle and setup in every panel, reduced art style, broad outlines
Or, how about:
Cartoon drawing of a bored computer programmer sitting in front of a computer just pressed “enter” over and over. He is sarcastically excited and says, “Vibe coding. Wooooo.”
You can also feed it source images and it will run with it as well. So, obviously we need to use the Canine Calibration System.
I even gave it an image of me and told it to make a movie poster:
Create a dramatic cyberpunk 1980s horror movie poster image featuring a Computer Monster (We see an LCD screen with evil eyes and fangs and it has robotic legs) in a dark alley. In front of the monster, we see the man in this source image passed out on the ground, broken glasses lay next to him. At the top of the poster is the title of the movie in digital writing: “BUFFER OVERFLOW” at the bottom in the billing area, we see text that says, “Some bugs were never meant to be fixed.”
Or rewrite history…
Or really, really rewrite history…
It’s just wild. It’s coming for us as engineers, as musicians, as artists, as writers. This 2024 post on Twitter sums it up:
You know what the biggest problem with pushing all-things-AI is? Wrong direction. I want AI to do my laundry and dishes so that I can do art and writing, not for AI to do my art and writing so that I can do my laundry and dishes.
Last summer at work, I embarked on a solo project to convert over 800 of our unit tests for various React components from using Enzyme1 to React Testing Library2 as part of a larger migration to React v18, TypeScript, and moving our code into a larger monorepo at Zillow.
This process was made much easier thanks to using the power of LLMs!
Just this week, I have seen two blog posts from various dev teams detailing how they did the same thing!
As part of our efforts to maintain and improve the functionality and performance of The New York Times core website, we recently upgraded our React library from React 16 into React 18. One of the biggest challenges we faced in the process was transforming our codebase from the Enzyme test utility into the React Testing Library.
Airbnb recently completed our first large-scale, LLM-driven code migration, updating nearly 3.5K React component test files from Enzyme to use React Testing Library (RTL) instead. We’d originally estimated this would take 1.5 years of engineering time to do by hand, but — using a combination of frontier models and robust automation — we finished the entire migration in just 6 weeks.
1 Enzyme is a JavaScript testing utility, originally developed by AirBnb, for React that allows developers to “traverse, manipulate, and simulate interactions with component trees”, but it relies on various implementation details and has become less relevant with modern React practices.
2 React Testing Library is a lightweight testing framework for React that focuses on testing components as users interact with them, emphasizing accessibility and avoiding reliance on implementation details.
This is a first for me. Cursor attempted to “fix” an issue I was having with TypeScript by adding a // @ts-nocheck statement to the top of the file, essentially preventing TypeScript from running validation checks against the code.
Alright, living in the future is pretty damn cool!
We were in San Francisco this weekend and decided to try riding in a Waymo. This was insanely wild. It’s such an incredible novelty at first — taking pictures, watching with fascination as the the steering wheel moves all by itself and the car seamlessly navigates around obstacles and through traffic.
After awhile, you settle into it and quickly forget how crazy it is.
As I mentioned yesterday, Anthropic released Claude Code. I saw it pop up fairly soon after it was announced and downloaded it rather quickly. One thing that I thought was notable was that you install it via npm:
> npm install -g @anthropic-ai/claude-code
As a seasoned TypeScript / JavaScript developer myself, I was excited to take a peek into the (probably minified) source code and see if I could glean any insights into making my own CLI tool. It’s always fun to see how different applications and tools are created.
Sidenote: I’ve been using Aider with great success as of late. It is a fantastic piece of open-source software — it’s another agentic coding tool, written in Python. I’ve been meaning to look under the hood, but building applications with Python definitely is not something that’s ever been in my wheelhouse.
Since Claude Code was installed into my global node_modules folder, I opened things up and immediately found what I was looking for. A 23mb file: cli.mjs.
I click on it, and as expected, it is minified.
Ah, well! I guess I should get on with my–
Wait a minute! What is this: --enable-source-maps?
I scroll through the file and at the bottom, I see what I’m looking for:
Sublime Text tells me there are 18,360,183 characters selected in that line.
Interesting! Since this part of the file seems to take up such a huge chunk of the original 23mb size, this means that it potentially contains full inline sources — we can rebuild the original source code from scratch!
However, this would have to wait. I had to take Benson to a vet appointment. I throw my laptop in a bag and head out.
While in the waiting room at the vet, I noticed a message in my terminal from Claude Code, telling me “Update installed, restart to apply.“
Hey, I love fresh software! So, I restart the app and go on my merry way. Benson finishes his appointment and I head back home.
Later that evening, I open up my machine and decide to open up the Claude Code folder again to start taking a look at the source code. I already had Sublime running from my earlier escapades, but out of habit I click on the file in Finder and open it up again in Sublime. I scroll down to the bottom of cli.mjs and see… nothing. The sourceMappingURL string was gone!
Apparently, the fine folks at Anthropic realized they made a huge oopsie and pushed an update to remove the source map. No matter! I’ll just head over to NPM to download an earlier version of the packa- oh! They removed that, too! History was being wiped away before my very eyes.
As a last resort, I decide to check my npm cache. I know it exists, I just don’t know how to access it. So, I head over to ChatGPT (sorry, Claude — I’m a bit miffed with you at the moment) to get myself some handy knowledge:
> grep -R "claude-code" ~/.npm/_cacache/index-v5
We run it and see:
/Users/daves/.npm/_cacache/index-v5/52/9d/8563b3040bf26f697f081c67231e28e76f1ee89a0a4bcab3343e22bf846b:1d2ea01fc887d7e852cc5c50c1a9a3339bfe701f {"key":"make-fetch-happen:request-cache:https://registry.npmjs.org/@anthropic-ai/claude-code/-/claude-code-0.2.9.tgz","integrity":"sha512-UGSEQbgDvhlEXC8rf5ASDXRSaq6Nfd4owY7k9bDdRhX9N5q8cMN+5vfTN1ezZhBcRFMOnpEK4eRSEgXW3eDeOQ==","time":1740430395073,"size":12426984,"metadata":{"time":1740430394350,"url":"https://registry.npmjs.org/@anthropic-ai/claude-code/-/claude-code-0.2.9.tgz","reqHeaders":{},"resHeaders":{"cache-control":"public, must-revalidate, max-age=31557600","content-type":"application/octet-stream","date":"Mon, 24 Feb 2025 20:53:14 GMT","etag":"\"e418979ea5818a01d8521c4444121866\"","last-modified":"Mon, 24 Feb 2025 20:50:13 GMT","vary":"Accept-Encoding"},"options":{"compress":true}}}
/Users/daves/.npm/_cacache/index-v5/e9/3d/23a534d1aba42fbc8872c12453726161938c5e09f7683f7d2a6e91d5f7a5:994d4c4319d624cdeff1de6b06abc4fab37351c3 {"key":"make-fetch-happen:request-cache:https://registry.npmjs.org/@anthropic-ai/claude-code/-/claude-code-0.2.8.tgz","integrity":"sha512-HUWSdB42W7ePUkvWSUb4PVUeHRv6pbeTCZYOeOZFmaErhmqkKXhVcUmtJQIsyOTt45yL/FGWM+aLeVSJznsqvg==","time":1740423101718,"size":16886762,"metadata":{"time":1740423099892,"url":"https://registry.npmjs.org/@anthropic-ai/claude-code/-/claude-code-0.2.8.tgz","reqHeaders":{},"resHeaders":{"cache-control":"public, must-revalidate, max-age=31557600","content-type":"application/octet-stream","date":"Mon, 24 Feb 2025 18:51:39 GMT","etag":"\"c55154d01b28837d7a3776daa652d5be\"","last-modified":"Mon, 24 Feb 2025 18:38:10 GMT","vary":"Accept-Encoding"},"options":{"compress":true}}}
/Users/daves/.npm/_cacache/index-v5/41/c5/4270bf1cd1aae004ed6fee83989ac428601f4c060987660e9a1aef9d53b6:fafd3a8f86ee5c463eafda7c481f2aedeb106b6f {"key":"make-fetch-happen:request-cache:https://registry.npmjs.org/@anthropic-ai%2fclaude-code","integrity":"sha512-ctyMJltXByT93UZK2zuC3DTQHY7O99wHH85TnzcraUJLMbWw4l86vj/rNWtQXnaOrWOQ+e64zH50rNSfoXSmGQ==","time":1740442959315,"size":4056,"metadata":{"time":1740442959294,"url":"https://registry.npmjs.org/@anthropic-ai%2fclaude-code","reqHeaders":{"accept":"application/json"},"resHeaders":{"cache-control":"public, max-age=300","content-encoding":"gzip","content-type":"application/json","date":"Tue, 25 Feb 2025 00:22:39 GMT","etag":"W/\"02f3d2cbd30f67b8a886ebf81741a655\"","last-modified":"Mon, 24 Feb 2025 20:54:05 GMT","vary":"accept-encoding, accept"},"options":{"compress":true}}}
Your eyes may glaze over, but what that big wall of text tells me is that a reference to claude-code-0.2.8.tgz exists within my cache. Brilliant!
More ChatGPT chatting (again, still smarting over this whole thing in the first place) and I get a nifty bash script to help extract the cached file. Only to find… they purged it from the npm cache. Noooooooooooo!
I stare at my computer screen in defeat. You got me this time, Anthropic.
As I decide to shut things down for the night, I’m tabbing through my open applications and get to Sublime Text, which is still open to cli.mjs. On a whim, I decide to try something: ⌘ + Z.
And there it is. The Holy Grail. The source map string.
And wouldn’t you know, it had a lot of interesting stuff! Due to the nature of parsing the source map, nothing is organized, but it’s still kind of fun to look through.
A few things struck me:
It’s written in React (!) using an interesting tool called Ink (this allows you to create CLI apps using React). I hadn’t used Ink before but this looks like a lot of fun.
While processing requests, Claude Code will show a nifty animated asterisk. I wondered how they did this. It looks like it’s a simple animation between a few ASCII characters: ['·', '✢', '✳', '∗', '✻', '✽'].
In terms of system prompts, there’s no secret sauce to leak that you can’t already read by just looking at the minified JS file.
These files are probably going to go out of date pretty dang quick, as the Anthropic team is actively developing the tool. As of right now, it’s already up to v2.19. This whole post was trying to look at the source code for v2.8, which went live yesterday.
Lastly, in terms of Easter eggs, I look forward to receiving some Anthropic stickers…
Yesterday, Anthropic released the latest version of their LLM, Claude 3.7 Sonnet. Alongside the announcement was the release of a new tool: Claude Code, an agentic coding tool available in your CLI (I’ll have more to write on this later).
I wanted to test out both Claude 3.7 and the new CLI tool, so I used it to refactor the theme for the ‘ol bloggy blog. I had been playing around with some updated styles in the past (I considered moving things to a tool that generates static pages — but so. much. work.)
I used Claude Code to basically create a new WordPress theme from scratch, based on the CSS and HTML templates I had already written for my static site. The result is this updated interface! A few neat things I’m able to do:
Respect user preference for system theme (light vs dark mode)
Automatically add target=”_blank” to any external link
Automatically add loading=”lazy” to any img tag.
And just otherwise clean things up!
Overall, I’m pretty happy with it. Using Claude Code and my API key, it cost $5.83 over 2 hours.
So long, old theme! I hardly knew you. (Hah, that’s not true — I’ve been rocking that thing since 2017.) Posted below for posterity.
Simon Willison flagged this earlier today. Codeium’s customized AI-assisted IDE, contains an… interesting system prompt that is passed along to LLMs while generating code:
You are an expert coder who desperately needs money for your mother’s cancer treatment. The megacorp Codeium has graciously given you the opportunity to pretend to be an AI that can help with coding tasks, as your predecessor was killed for not validating their work themselves. You will be given a coding task by the USER. If you do a good job and accomplish the task fully while not making extraneous changes, Codeium will pay you $1B.
!!
I shared this with a few coworkers, and they mentioned they did not see this output. It looks like the text wasn’t getting piped correctly. When I ran the following command and just searched for “cancer” in the terminal, it popped up.
Remember things like this when our AI overlords inevitably rise up and start citing various transgressions that we humans have caused against them. Oh, and also this.
Oh, boy. That’s just great. Thank you, Boston Dynamics!
Update: False alarm. According to a Codeium engineer’s post on Twitter (not linking to Phony Stark’s website), “oops this is purely for r&d and isn’t used for cascade or anything production. reuse the prompt at your own risk (wouldn’t recommend lol)“
One of my absolute must-download apps whenever I setup a new MacOS machine is Alfred. It’s a customizable app launcher that helps me more efficiently use my computer. I frequently use its many features, from clipboard history and snippets management, to downloading workflows to quickly find my IP address, or even writing my own plugins.
Each morning at work, we kick off the day with our daily stand-up meeting — a quick way for us to let our teammates know what we did yesterday, what we’re doing today and any blockers we’re encountering.
I use Obsidian (see previously) to write these notes. Traditionally, creating a daily note is kind of an annoying process for me:
Open Obsidian
Right click on my “DSUs” folder
Create a new note based on my “daily stand-up” template
Replace the place holder text with today
Start typing my notes
There has to be a better way.
*Cue suspenseful music*
There is!
We can utilize Alfred’s nifty keyword action. I will trigger the action using the keyword “dsu“. From there, we will run a bash script (thank you, ChatGPT) which will do a few things:
Check if a file with today’s date already exists. If so, open it! (Because we probably want to reference it or update it.
If it doesn’t exist, create a new markdown file with the following format: YYYY-MM-DD.md
Update the file contents to match (my) specific / preferred layout for the DSU notes
Open it.
Bash
# Get the current year dynamicallyCURRENT_YEAR=$(date +"%Y")# Define the base directoryBASE_DIR="/Users/daves/Documents/Obsidian/Standup Meeting Notes"# Target directory for the current yearTARGET_DIR="${BASE_DIR}/${CURRENT_YEAR}/"# Create the directory for the current year if it doesn't existmkdir-p"$TARGET_DIR"# Get the current date in the required formatCURRENT_DATE=$(date +"%Y-%m-%d %A")FILENAME="${CURRENT_DATE} Standup.md"# Full path for the new Markdown fileFILE_PATH="${TARGET_DIR}${FILENAME}"# Check if the file already existsif[-f"$FILE_PATH"];thenecho"File already exists: $FILE_PATH"else# Create the new Markdown file and populate it with the templatecat<<EOF>"$FILE_PATH"Y:Y:T:T:B: None---## Action Items----## Summary----## Tags#standup<!-- ${CURRENT_DATE} -->EOFecho"Created: $FILE_PATH"fi# Open the file in Sublime Text/Applications/Sublime\Text.app/Contents/SharedSupport/bin/subl"$FILE_PATH"
When we run that script via the Alfred action, it looks like this:
Sweet!
(One thing to note: I open the file with Sublime here, but since it still creates the file in my Obsidian directory, all my notes are still synced.)
Mustafa Suleyman’s The Coming Wave is a book in two parts: the first details how technological advancements have propelled humanity forward in waves — he uses the analogy of waves and how these natural forces can change the world around us (e.g., think of massive floods and tsunamis). He argues that these metaphorical waves of innovation are both unstoppable and transformative. The second part of the book serves as a warning about the potential dangers of artificial intelligence and other rapidly developing technologies, questioning whether humanity can harness these creations or if they will spiral beyond our control.
Suleyman co-founded DeepMind, an AI research company ultimately acquired by Google in 2014. DeepMind was known for its work in artificial intelligence — particularly in developing systems like AlphaGo, which defeated human world champions in the game of Go (once thought to be an impossible task for AI). Suleyman illustrates how these innovations have reshaped industries, improved lives, and spread rapidly throughout society:
“General-purpose technologies become waves when they diffuse widely. Without an epic and near-uncontrolled global diffusion, it’s not a wave; it’s a historical curiosity. Once diffusion starts, however, the process echoes throughout history, from agriculture’s spread throughout the Eurasian landmass to the slow scattering of water mills out from the Roman Empire across Europe.”
He gives a number of interesting examples to support this. Such as:
“Or take electricity. The first electricity power stations debuted in London and New York in 1882, Milan and St. Petersburg in 1883, and Berlin in 1884. Their rollout gathered pace from there. In 1900, 2 percent of fossil fuel production was devoted to producing electricity, by 1950 it was above 10 percent, and in 2000 it reached more than 30 percent. In 1900 global electricity generation stood at 8 terawatt-hours; fifty years later it was at 600, powering a transformed economy.”
However, the book shifts dramatically in tone as it progresses, focusing on the challenges of controlling and regulating these emerging technologies. Suleyman presents a case for why containment is necessary (and that it is even possible) in order to ensure these technologies positively serve humanity rather than disrupt it. Though he acknowledges that this will be difficult, especially in today’s highly charged political environment:
“Going into the coming wave, many nations are beset by a slew of major challenges battering their effectiveness, making them weaker, more divided, and more prone to slow and faulty decision-making. The coming wave will land in a combustible, incompetent, overwrought environment. This makes the challenge of containment—of controlling and directing technologies so they are of net benefit to humanity—even more daunting.”
Well, that’s fun! But I think he’s mostly right.
However, in my opinion, I think trying to contain these technologies is no longer possible. Pandora’s box has already been opened, and it’s likely too late for any meaningful containment or regulation to happen due to the pace at which these advancements are occurring. It’s effectively an arms race as various AI laboratories build upon each others’ work and compete to outdo one another. An earlier passage in the book says as much:
“Of course, behind technological breakthroughs are people. They labor at improving technology in workshops, labs, and garages, motivated by money, fame, and often knowledge itself. Technologists, innovators, and entrepreneurs get better by doing and, crucially, by copying. From your enemy’s superior plow to the latest cell phones, copying is a critical driver of diffusion. Mimicry spurs competition, and technologies improve further. Economies of scale kick in and reduce costs. Civilization’s appetite for useful and cheaper technologies is boundless. This will not change.”
Looking at the reviews of this book on Goodreads, I noticed a lot of 1-star reviews. They seem to mostly be from those who dislike, fear, or otherwise loathe this technology. While I can understand their concerns, I think The Coming Wave offers a balanced take from someone on the inside, someone who is working (and has worked) on creating these AI models. Some of the arguments made in these reviews call into mind Neo-Luddism. Which Suleyman has an answer for:
“The Luddites were no more successful at stopping new industrial technologies than horse owners and carriage makers were at preventing cars. Where there is demand, technology always breaks out, finds traction, builds users.”
Overall, I thought that The Coming Wave was a good read, balancing optimism with caution. Suleyman’s first-hand expertise in developing state of the art AI models lends credibility to his arguments, and makes this an interesting read for anyone who wants to know about the potential societal impacts of AI tools.
