iiinova — where your digital self keeps evolving

Brandon Rohrer @brandonrohrer.com · 1h

AWS is fighting hard to keep up with GPU demand on the West Coast today, and they are losing.

000

Brandon Rohrer @brandonrohrer.com · 1h

jeez claude, rein it in a bit. I don't get paid by the line.

001

Brandon Rohrer @brandonrohrer.com · 29/09/2026

Cool Python trick: Sometimes you want functions to have keyword arguments, but you also want them to be required. This is especially useful when you're passing required arguments using dictionary expansion, like `function(**arg_dict)`.

100

Brandon Rohrer @brandonrohrer.com · 29/09/2026

Optimizing models with lots of hyperparameters and options is a slog that usually requires a combination community wisdom, obscure blog posts, and tedious trial and error. Automated methods tend to rely on strong assumptions of smoothness or brute force their way through every permutation.

110

Reposted by Brandon Rohrer

danah boyd @zephoria.bsky.social · 24/09/2026

Today is Pub Day for "Data Are Made, Not Found: A Story of Politics, Power, and the Civil Servants Who Saved the US Census"!!! ::bounce:: Please support me by buying a copy of the book or asking your library for a copy! press.uchicago.edu/ucp/books/bo...

1238595

Brandon Rohrer @brandonrohrer.com · 16/09/2026

Hey US eng friends, if you want to give Patreon a shot: Staff SWE, Data Infrastructure jobs.ashbyhq.com/patreon/e8f0... Senior MLE, Infrastructure (on my team) jobs.ashbyhq.com/patreon/722d... Staff SWE, Backend Platform jobs.ashbyhq.com/patreon/c277...

jobs.ashbyhq.com

Staff Software Engineer, Data Infrastructure

Patreon is a media and community platform where over 300,000 creators give their biggest fans access to exclusive work and experiences. We offer creators a variety of ways to engage with their fans an...

120

Brandon Rohrer @brandonrohrer.com · 15/09/2026

Three days of automated parameter sweeps saved me 15 minutes of Internet searches!

0140

Brandon Rohrer @brandonrohrer.com · 08/09/2026

added type hints and ran mypy on some code I considered tight. It was like shining a black light in a hotel room.

040

Brandon Rohrer @brandonrohrer.com · 31/08/2026

Diving in to Python typechecking and stumbled on this @vickiboykis.com post vickiboykis.com/2023/12/11/w... The tldr: "The result of the deep dive is that I now no longer trust anything in the Python typing ecosystem." I'm now confused as ever, but on a higher level and about more important things

vickiboykis.com

Why if TYPE_CHECKING?

Typechecking is brittle yet important

070

Brandon Rohrer @brandonrohrer.com · 22/08/2026

Josh, Luis, and I had a great time chatting the other day and recorded in case you'd like to listen in www.youtube.com/live/Yx-ZkLf...

youtube.com

TRIPLE BAM!!! With Josh, Luis and special guest Brandon Rohrer

YouTube video by StatQuest with Josh Starmer

000

Brandon Rohrer @brandonrohrer.com · 20/08/2026

If you’re into such things, I’m going to be chatting with Josh Starmer and Luis Serrano (two of the best ML educators I know) in a YouTube livestream, answering viewer questions, at 11:00am EDT Thursday (tomorrow/today). 8am PDT, 3pm UTC, 5pm CEST m.youtube.com/live/Yx-ZkLf...

m.youtube.com

TRIPLE BAM!!! With Josh, Luis and special guest Brandon Rohrer

YouTube video by StatQuest with Josh Starmer

021

Brandon Rohrer @brandonrohrer.com · 10/08/2026

My Artisanal Language Model for proofreading continues to evolve. Pairing forward and backward first-order Markov models is proving to be just good enough to merit further exploration. brandonrohrer.com/alms_composi...

five plots showing five different proofreading evaluation scores: capitalization, grammar, missing words, punctuation, spelling. In each case, as the error threshold for identifying a proofreading error increases from 1e-5 to 1e-2, precision drops from 100% to very small and recall rises from very small to 100%. The crossover point tends to be in the 30-40% range at around 0.0002

110

Brandon Rohrer @brandonrohrer.com · 08/08/2026

RSS is the vinyl records of the web. And the Current RSS reader is the $5000 turntable whose clean design matches the medium. Except it’s only $10. www.currentreader.app Built by one designer with a vision ( @terrygodier.com ), Current shows what the web can be.

currentreader.app

Current - A River of Reading

Current rethinks RSS for the modern reader. Your feeds flow like a river. No inbox anxiety, no unread counts. Just beautiful reading.

370

Brandon Rohrer @brandonrohrer.com · 04/08/2026

There are several command line incantations that I have had to look up at least a dozen times. Finding a string in Python files grep -r --include \*.py 'string I am looking for' . Find files by name find . -name '*partial_name*'

110

Reposted by Brandon Rohrer

valyriansteelers.bsky.social @valyriansteelers.bsky.social · 27/07/2026

Listening to the Dungeon Crawler Carl books with Soundbooth Theater leads to really long walks because I can't stop listening. They are a blast!

041

Brandon Rohrer @brandonrohrer.com · 26/07/2026

Heads up ruff users - with the release of 0.16.0 this week the number of default rules went up from 59 to to 413. This means that if you're ruff version auto updates, your CI pipelines might start failing on you all of a sudden.

143

Brandon Rohrer @brandonrohrer.com · 25/07/2026

Living small is part of the artisanal process. The constraints are not a barrier to the final product. They are an important shaping force. You can't come in at the end and magically shrink it. You can only build small if you start small and work with what you've got as you go. brandonrohrer.org

Book Project: Artisanal Language Models
Chapter 1: Artisanal Language Models
Chapter 2: Build a custom tokenizer
Chapter 3: Define a task and write evals
Chapter 4: Build an end-to-end prototype
Chapter 5: ALM v2, First-order Markov model
Chapter 6: ALM v3, Second-order Markov model
Chapter 7: ALM v6, Sparse second-order Markov model
Chapter 8: ALM v14, The Search for Data

162

Brandon Rohrer @brandonrohrer.com · 21/07/2026

Artisanal Language Models take a step closer to being able to do proofreading. Trained and hosted on an old Mac. These are small but mighty. Kind of. Aspirationally mighty, at least. brandonrohrer.org/alms_data.html

brandonrohrer.org

It took a little time to figure out how to properly download Project Gutenberg texts at scale, but I finally set up three new training corpuses:

011

Brandon Rohrer @brandonrohrer.com · 08/07/2026

the biggest difference I've noticed between data scientists and machine learning engineers is that MLEs will do absolutely anything to avoid looking at their data

1112

Brandon Rohrer @brandonrohrer.com · 28/06/2026

don't touch those! those are my emotional support patreons!

020

Brandon Rohrer @brandonrohrer.com · 28/06/2026

My favorite thing to do is find a narrow problem that doesn't have a good solution, and then build one. Here are the highlights, from my blog. brandonrohrer.org/blog.html#al...

Algorithms and Methods
Evolutionary Powell's method for hyperparameter tuning
k-nearest neighbors adaptive feature weighting
k-nearest neightbors data reduction
k-sparse neural network layer
Naive Cartographer , a Markov Decision Process learner
oknn, an online variant of kNN
Pathfinder, a many-to-many shortest path algorithm
Sharpened Cosine Similarity, an alternative to convolution for learning 2D features in neural networks
Ziptie, an unsupervised feature creation algorithm

130

Brandon Rohrer @brandonrohrer.com · 27/06/2026

I shut down by online courses at End-to-End Machine Learning 18 months ago. Wrote a blog post and everything. But the platform I was using hasn't bothered to take them down. So they're just sitting there, all for free. Prego. end-to-end-machine-learning.teachable.com

A screenshot from the link showing cards for courses on decision trees, polynomial optimization, k-nearest neighbors, multilayer neural networks, autoencoders, and convolutional neural networks

051

Brandon Rohrer @brandonrohrer.com · 22/06/2026

Efficiency maxxing is problematic for lots of reasons but a fundamental reason is that it always implies near term efficiency.

120

Brandon Rohrer @brandonrohrer.com · 21/06/2026

This next round of Artisanal Language Model improvements are mostly focused on efficiency rather than dramatic algorithmic improvements. This ALM is a proofreading tool for English prose. brandonrohrer.org/alms_somm_sp...

brandonrohrer.org

After some trial and error with a few sparse representation concepts, I settled on one that takes advantage of one of Python's strengths: dictionaries. The sparse second-order model keeps two running dictionaries: one full of bigram counts and one for trigram counts.

100

Brandon Rohrer @brandonrohrer.com · 14/06/2026

The Cheers restaurant is in my neighborhood. Kilts and bagpipes now on every corner. www.youtube.com/watch?v=nprg...

youtube.com

Rosco McLelland's World Cup anthem! #BreakingTheNews

YouTube video by BBC Scotland

000

Brandon Rohrer @brandonrohrer.com · 06/06/2026

Old school language models, part 2: Second-order Markov Models This is the next stop in my Artisanal Language Model development tour. If a first-order Markov model has a context length of 1, then a second-order has a context length of 2. brandonrohrer.org/alms_somm.html

model name capitalization punctuation spelling
random proof_01 (12) 26 (14) 20 (13) 24
FOMM_00 proof_02 (7) 98 (7) 98 (7) 98
SOMM_00 proof_03 (6) 100 (6) 94 (6) 98
FOMM_01 proof_04 (8) 100 (8) 98 (8) 98
SOMM_01 proof_05 (8) 100 (7) 90 (7) 96

110

Brandon Rohrer @brandonrohrer.com · 03/06/2026

I don't often brag about my company, but today I make an exception. Our CEO, folks: youtu.be/36jxNeV5L1Q?... (part of the ongoing Reckless Ben / Bricks and Minifigs / American Fork PD drama)

youtu.be

Take Down Notification: Reckless Ben’s Patreon Account

YouTube video by JackConteExtras

131

Brandon Rohrer @brandonrohrer.com · 01/06/2026

Sometimes AI scraper bots need a rest. You can give them a peaceful little playground to romp around in. Just drop this URL as a tiny hyperlink somewhere on your blog. Reviews are flooding in. Bots like this tarpit so much that they never leave. scienceispoetry.net

scienceispoetry.net

SEANCE IS POTTERY

020

Brandon Rohrer @brandonrohrer.com · 29/05/2026

The earliest Large Language Models were Markov models (a.k.a. Markov chains). They are like LLMs with a context window of 1 token. As you might guess, they are OK at some things but not awesome.

220

Brandon Rohrer @brandonrohrer.com · 18/05/2026

So apparently you can become a Patreon creator just put stuff up. For free. Or for money. Up to you. www.patreon.com/posts/findin...

patreon.com

Finding Your Way | Brandon Rohrer

Finding Your Way by Brandon Rohrer on Patreon. Join Brandon Rohrer's community for exclusive content and updates.

000

Brandon Rohrer @brandonrohrer.com · 14/05/2026

Hi Data Scientist friends! Come work with me at Patreon. Our DS team is hiring a Senior DS for some really fun work on recommender systems. (This is someone I'll be talking with a lot, so I'm heavily invested.) jobs.ashbyhq.com/patreon/f8f0... #DataScience

jobs.ashbyhq.com

Senior Data Scientist, Feed Relevance

193

Brandon Rohrer @brandonrohrer.com · 01/05/2026

May inspo. I’m too chicken to post this on LinkedIn

Monthly calendar showing the month of May. Gorgeous full page shot of a dirt trail between wildflowers on a mountain disappearing into trees. 80 point font declaring “ failure is always an option”

0111

Brandon Rohrer @brandonrohrer.com · 01/05/2026

Look, there’s only so much I can do. Any effort I put into my appearance comes out of something else. I’ve decided to adopt the practice of looksminning. I now identify as an erudite bog-goblin.

050

Brandon Rohrer @brandonrohrer.com · 30/04/2026

*smashes the Buy Now button*

020

Reposted by Brandon Rohrer

Iris Meredith @iris-meredith.bsky.social · 22/04/2026

It is once again time for me to reintroduce myself, I think. I'm Iris: I write a blog at deadsimpletech.com/blog about the impacts of the tech industry on culture and humanity in general. I also work as a technical consultant and coach/mentor in the data, infrastructure and web spaces.

deadTech - the blog
In-depth articles from a straightforward engineer
deadsimpletech.com/blog

My blog started off as an attempt at content marketing. It degenerated into critical analysis of tech and tech trends pretty much immediately.

I write about the modern tech infrastructure and its impacts on culture and humanity. In times like these, understanding how tech is reshaping our daily experience and how it might reshape it differently is important if we want to live relatively happy lives, whatever the world brings.

Support our work here:

patreon.com/c/IrisMeredithAndHerBlog
en.liberapay.com/iris_meredith

2309

Brandon Rohrer @brandonrohrer.com · 29/04/2026

Coding Hobgoblins Consistent style makes code easier to read and helps bugs to be more visible. I aim to keep my code mostly consistent and mostly in line with the recommendations of PEP 8, but if I have good reason to deviate I don't hesitate.

220

Brandon Rohrer @brandonrohrer.com · 29/04/2026

This from @anildash.com gives me hope. www.anildash.com/2026/04/28/o... It's a success story of people who have a problem and use ML to solve it. It features 1. domain experts 2. curated training data 3. generous open source sharing 4. a flood of community support This is what ML can be

anildash.com

(One) Good AI Is Here - Anil Dash

A blog about making culture. Since 1999.

140

Brandon Rohrer @brandonrohrer.com · 28/04/2026

This gem from @awoodruff.bsky.social sits in the Venn diagram intersection of data, art, and Beantown. andywoodruff.com/posts/2026/b...

A map of where people work in the Boston area shown as overlapping bubbles. Downtown and back Bay are covered heavily and there is a strong representation in Kendall Square, MIT, Harvard, Longwood, and Boston University.

A map showing distance in Smoots from the Boston side of the Harvard Bridge with radiator up to 2500 Smoots that covers all of Boston and Cambridge

The cover of the book, Boston in 50 Maps by Andy Woodruff. It is a very old timey hand drawn map of Boston.

A map showing how many Dunkin’ Donuts are reachable within a 5 to 10 minute drive from every location in Boston. In downtown Boston, it’s 20 or more Dunkies

031

Reposted by Brandon Rohrer

Candyce 🌊🦋💙☕️🩵 Want New Blue Connections? FOLLOW ME 😊 @candycemv1.bsky.social · 27/04/2026

🤷🏻‍♀️🤷🏻‍♀️🤷🏻‍♀️

149112632114

Brandon Rohrer @brandonrohrer.com · 28/04/2026

in fantasy stories I've seen a recurring theme of naming things. A true name of a thing has great power and is inconveniently long. Ents in Lord of the Rings. Wolves in Wheel of Time. Sorcery in A Wizard of Earthsea. This is how I like to name my Python variables.

0151

Reposted by Brandon Rohrer

Ky @ky.fyi · 24/04/2026

I wrote about why I quit my job, and how weird and tiring tech feels these days.

ky.fyi

Do I belong in tech anymore?

On quitting, the spread of AI, and the loss of an ideal.

1281791545

Brandon Rohrer @brandonrohrer.com · 25/04/2026

in which @vickiboykis.com reveals How to rekindle the joy in ML Hopeful and grounded and a delight to read.

070

Reposted by Brandon Rohrer

Mark Riedl @markriedl.bsky.social · 24/04/2026

I have saved The mantises That were on The grill And for which You were probably Oh I don’t know What for Forgive me They were tiny So cute And adorbs

182

Reposted by Brandon Rohrer

Vicki @vickiboykis.com · 24/04/2026

Easy ways to reduce your token spend. No one will do these three weird tricks to write less code because they’re so boring: 1. Talk to other people in your org to get better requirements 2. Have humans write good documentation 3. Make your internal search tool better

1319220

Reposted by Brandon Rohrer

Adam Austin @ataustin.bsky.social · 21/04/2026

*sexiest job of the 21st century* I whisper to myself as I move roadmap tiles, reschedule three meeting conflicts, and update the requirements document to reflect new governance standards #dataBS

0286