Patrick Martin

@historyinmemes This is the machine Americans sit on every tax season.

My interpretation of prompt engineering is this: 1. A LLM is a repository of many (millions) of vector programs mined from human-generated data, learned implicitly as a by-product of language compression. A "vector program" is just a very non-linear function that maps part of the latent space unto itself. 2. When you're prompting, you're fetching one of these programs and running it on an input -- part of your prompt serves as a kind of "program key" (as in database key) and part serves as program argument(s). Like, in "write this paragraph in the style of Shakespeare: {my paragraph}", the part "write this paragraph in the stye of X: Y" is a program key, with arguments X=Shakespeare and Y={my paragraph}. 3. The program fetched by your key may or may not work well for the task at hand. There's no reason why it should be optimal. There are lots of related programs to choose from. 4. Prompt engineering represents a search over many keys in order a find a program that is empirically more accurate for what you're trying to do. It's no different than trying different keywords when searching for a Python library. 5. Everything else is unnecessary anthropomorphism on the part of the prompter. You're not talking to a human who understands language the way you do. Stop pretending you are.

"Bluefish: A Relational Grammar of Graphics" by @joshmpollock and co. Preprint: arxiv.org/pdf/2307.00146…

I just released ANTLR Lab, a new playground for learning about ANTLR or experimenting with and testing grammars! Feedback welcome. :) My first js/css/html app (#painful but #productive). You can use my site or run locally: lab.antlr.org

life of a DNS query wizardzines.com/comics/life-of…

Everyone: dafuck are you doing? Me: confused trying to use a new API without looking at the docs 🤔🤣

Get a cat they said, it will reduce your stress

@thebmbennett Linear scalability

Quick: What's a data/tech thing that sounds real but is actually fake?

(Via this cool article about the Antikythera mechanism) twitter.com/gregegansf/sta…

Classic reverse engineering story – you spend a century trying to figure out how the damn thing works and then you discover that there's a PDF from the manufacturer with all the details somewhere on their site.

Launched a new website, explained.ai, dedicated to giving deep but intuitive explanations of machine learning and related topics.

@stevenstrogatz @MIT Great read! Most of this is applicable to any field involving knowledge transfer. The world has lost a very wise man.

Along with being a great mathematician, Gian-Carlo Rota was a charming gentleman (he was very kind to me when I was a young professor at @MIT). Plus he was a wise, witty, and opinionated writer. Here he shares "Ten Lessons I wish I had been Taught": alumni.media.mit.edu/~cahn/life/gia…

@the_antlr_guy @Google Can’t wait to see what this phase of your career brings, ANTLR remains my favorite tool when I am in need of a full featured DSL. Your achievement has enabled others to achieve so much more! Best of luck!

Excited to announce that today is my first day as a tech lead at @Google, after 20 years in academia! Betcha didn't see that coming! I plan to continue working on open-source projects on the side (e.g., ANTLR, TensorSensor, explained.ai, etc).

About 2 months ago I went to review a product I bought from Amazon and I ran into this message

Interesting summary of new features between #Java8 and #Java17 by @VaverDariush. Time to switch to Java 17! pretius.com/blog/java-17-f…

Programming languages ranked by how much electricity they use: bit.ly/ProgEnergy (v/@DavidCasselTNS @thenewstack)

The History of Top Programming Languages from 1965 to 2019! #Coding #DataScience #Analytics #IoT #Python

@micahstubbs You might try npm i cli-progress

I welcome related work & bikeshedding over code quality metrics :-)

wrote a quick #nodejs script to measure my progress converting a #React #JavaScript project to #TypeScript node index.js measuring progress converting [".js",".jsx"] to [".ts",".tsx"] 7 [".js",".jsx"] files 5 [".ts",".tsx"] files 42% converted github.com/micahstubbs/co…

This is an amazing idea. Seems so obvious. I don't think you'd need a robotic glove to accomplish this though. Video recognition could so the trick quite nicely, killer app idea. Also, these guys look so young. I must be getting old.

@DataRemixed I think that the purest goal of data visualization is to offer insight. A simple line chart over time or bar charts would have done better; if the goal was to communicate comparative gender literacy. Having said that, I dig new and innovative ways to show the same thing.

I've seen time going from left-to-right & right-to-left but I think this is the first time I've seen both on the same chart. I misread it at first glance, thinking male rates were dropping, but another "non data person" I showed got it right away. What do you think about it?