How to Brew Espresso ↗
[YouTube embed] I’ve been geeking out on espresso recently since learning about its history and how today’s equipment and beans have changed, so the rules-of-thumb I’ve heard about may no...
Ben Tsai
Latest posts
Monospace
In my latest venture towards productivity bliss, I’ve been looking at a lot of different typefaces to fit with my plain text system. As an engineer, I have a handful...
Fraudulent
Fraudulent. That’s the word I keep coming back to when I reflect on the experience of using chatbots and agents. These machines produce an output using conversational language and are...
Comprehension is the job
I’ve already referenced Addy’s Comprehension Debt piece, but I think it is worth highlighting this quote: “Making code cheap to generate doesn’t make understanding cheap to skip. The comprehension work...
The paradox: to get better at ai, you...
The paradox: to get better at ai, you need to not use ai.
Performative
I recently read this piece on one of my favorite topics entitled On genAI: Was prototyping really a bottleneck? by Frank Elavsky: “And so large-language models give us performative fidelity;...
Software is people
One pillar of my origin story is when I realized the software I’m building exists as part of a system whose goal is to serve human beings. Secondarily, the process...
Outsourcing thinking ↗
Erik Johannes Husom’s piece entitled Outsourcing thinking resonated with me. He highlights the use of LLMs in personal communication and writing: “Direct communication is not only about the information being...
It’s Okay ↗
I wrote a LinkedIn post: “I used to have some regrets. I missed the Web 2.0 wave in the 2000s. I didn’t work on webapps until 2016. I missed the...
Thinking modes ↗
From Robin Sloan’s blog: “Here is one distinction among several: this process can only compound — the models can only “think” by spooling out more text — while human thinking often does the opposite:...
The simulation of judgment in LLMs ↗
The simulation of judgment in LLMs “While models often match expert outputs, our results suggest that they may rely on lexical associations and statistical priors rather than contextual reasoning or...
Text Is Best
I wasn’t intending to rework my tasks and notes system. It just happened to me. At the end of the day, I’ve ended up with a lightweight process that is one...
It’s a Trap
For a long time, I’ve been trying to articulate why interacting with an LLM is so irksome. Essentially, it is because the text being generated does not originate from a...
Democratizing Knowledge
Marcus Hutchins (of WannaCry fame) is my new favorite follow. Here’s a quick sample of him countering the claim that AI “democratizes knowledge.”: “LLMs chatbots are not democratizing knowledge. They're putting...
You Think?
Should you use an LLM to help you “write?” Let’s say I take some notes and thoughts I have about a particular topic and input into an LLM. I then...
Do the Work
A few months ago, I was inspired by this remark from world-class violinist Hilary Hahn, speaking on “natural talent”: “At some point, everyone’s got to do the work.” In the...
Who is more foolish...
Who is more foolish? The fool, or the fool who uses ai?
[#TheCompoChallenge]
[#TheCompoChallenge]
Analog
For cyber Monday, I splurged and purchased Ugmonk’s daily and weekly system. I also threw in an hourglass. You can see that so far the system is not keeping me...
Scratchpad
Constraints are liberating. I’ve been enjoying Sindre Sorhus’s laser-focused apps like Gifski, Menu Spaced, and Plain Text Editor. Most recently he released Scratchpad and it’s found its way into a...
Prototype for Whom?
When we create prototypes, I rarely see a consideration around who the audience is. That’s a huge missed opportunity. When I was participating in a design sprint activity earlier this...
Will AI go the way of the Concorde? ↗
My colleague Lindsey M. West Wallace PhD wrote a piece entitled Will AI go the way of the Concorde? where she thinks through the ills of AI by way of a...
Not Another Chatbot!
Okay, we gotta talk about chatbots. No one wants them, but everyone’s adding one to their product. This frustrates me for several reasons. Fix your websiteFirst, we know that LLMs...
Disdain for AI
I’m surprised I haven’t written more about my disdain for AI. I think it’s because the hype around it is exhausting and only proliferating each day. There’s something new every...
WeblogPoMo2024
I participated in WeblogPoMo2024 last month. Instead of committing to a specific cadence—like every day—I dipped my toes in, and I’m glad I did. I started strong, with threeconsecutivedays. I gave...