Archive

James Wilson …

We are entering an era where someone might use a large language model to generate a document out of a bulleted list, and send it to a person who will use a large language model to condense that document into a bulleted list. Can anyone seriously argue that this is an improvement? via Ted Chang in …

Training may want the large data center, but we’ve long since hit the point of diminishing returns. There is effectively no more text to train on, as even the LLM systems of a few years ago were trained on almost all the coherent text in existence via Pivot to AI

So good. One Battle After Another 🍿

Finished reading: Pereira Maintains by Antonio Tabucchi 📚

Boring machine learning is where it’s at go grab a spreadsheet and figure out how to get the best result on a boring economics problem with a boring algorithm; Don’t worry so much about making a painting or movie with GANs, we’re already really good at doing that and enjoy doing …

Store git credentials for a day from the command line. As of Aug, 2021, a ‘personal access token’ must replace your password. git config --global credential.helper "cache --timeout=86400" via https://stackoverflow.com/a/5343146/992999

Python decorators: 

I finally understand Python decorators!

Link list of programming tips: Link list of programming tips A crowd-sourced list of recommendations for learning good programming style from the lab group. Software Design in Python Pragmatic Programmer Clean Code Philosophy of Software Design Code Craft The Missing README Beyond the Basic Stuff Refactoring code All the little …

iA Writer to micro.blog: I just discovered that iA Writer publishes to micro.blog. How cool! Am going to see if I can use this to improve my writing habits as per Andrew Gelman's recent comment: Eventually everything makes its way from conversation to blog to publication. A great philosophy.

Far from being an aberration, Dominic Raab might be the right man for the job – an out-of-office foreign secretary for an out-of-office country. Via Marina Hyde

… working through the logical implications of our assumptions: What’s the purpose of mathematical modeling? « Statistical Modeling, Causal Inference, and Social Science Scientists — not just in epidemiology, but in physics, ecology, climatology, economics and every other field — don’t build models as oracles of the future. For them, a model “is just a way of …

Machine learning toolkit in the browser from a single docker image. docker run -p 8080:8080 mltooling/ml-workspace:0.12.1

Today I learned that to access netrw (Vim’s inbuilt file browser) I need to call :Explore.

dalex.drwhy.ai On a mission to responsibly build machine learning predictive models

Git submodules: Maybe the nicest explanation I’ve read so far. But then, they should know!

By harnessing randomness, a new algorithm achieves a fundamentally novel — and faster — way of performing one of the most basic computations in math and computer science.: Not just a cool scientific advance, but a very cool explanation of a new technique. For that matter, a lovely explanation of matrix multiplication for the non-mathematician. New Algorithm Breaks Speed Limit for Solving Linear Equations By harnessing randomness, a new algorithm achieves a …

Karl Broman: What a cool set of resources including notes on R, make and more!

Reflow a comment in Vim: Visually select the text then gq

Getting Ofelia to work: I followed and modified the instructions here. This was much easier than trying to make do with the readme. The key insight here is that you need to leave something running in the foreground. How do I keep Docker containers running in the background? If you would like to keep your container running …

Vim tips: file name completion? (triggered with <c-x><c-f>)

A brief tutorial on decision curve analysis: A simple, step-by-step guide to interpreting decision curve analysis

50 Years of Data Science ...: 50 Years of Data Science: Journal of Computational and Graphical Statistics: Vol 26, No 4: This paper is a great find. Not the least because the argument (statistics versus data science) was already in full swing 50 years ago. I have no problem with predictive modelling, but it is a different task. …

Science Isn’t Broken | FiveThirtyEight That variation [in results] occurs because science is hard.

Two photo-essays from work I cry a lot on the train home': London medics fight to save Covid patients A baptism of fire': medical volunteers at a Covid ICU – photo essay