Byron Galbraith

Happy Father's Day! Hope you're back home by now

A Rivulet program in the form of coloured lines meandering over a yellow background with faint grey gridlines. The red line on the left traces a vaguely stag-like image with three-tined 'antlers'. On the right are orange, green and blue lines tracing a vaguely castle or maze-like structure with crenellations on the top edge. The program calculates the factorial of some input value, which in this case is 7! =5,040. The Rivulet source is 1 ╵╰─ ╵╵╰──╮ 2 ╮ ╮ ╭ ─╯╷ 3 ╮╷ ─╮│ │╭──╯ 5 │╭ ╭╶╵╰─╯│ │╷ 7 ─╮ ╭─ ││ │ ╰───╯ │╰──│ 11 ╭─ │ │ ╭─ │╰─╯ ╭ ╰───╯╷ 13 │ │ ╭─│ │╭─│ ╭─╮│ 17 │ ╭──╯╭───╯ │╭────╯│ │ │ ││ 19 │╭──╯ ╭─╯╭────╯│ │ ╰───╮ │ ││ 23 ╰───╯╯ ╯ ╯ ╮╯ ╰───╯╮ ─╮╷ │╴╯│ 29 ╰─── ╰───╯ ╭╯ ─╯ 31 ╭ ╭╯ 37 │ ╭─╯ 41 ╰─╯ 43 ╷

@dtemkin.bsky.social 's Rivulet esolang prompts ideas around code and #datavis comprehension. How do we make sense of visualizations when we are unfamiliar with the 'grammar' of their design?

An introduction Rivulet:

observablehq.com/@jwolondon/r...

An editor:

observablehq.com/@jwolondon/r...

5-panel comic. (1) [teacher with long hair next to whiteboard] TEACHER: I’m supposed to give you the tools to do good science. (2) [teacher addressing students] But what *are* those tools? Methodology is hard and there are so many ways to get incorrect results. What is the magic ingredient that makes for good science? (3) TEACHER: To figure it out, I ran a regression with all the factors people say are important: [embedded list in sub-panel, cut off at end] Outcome variable: correct scientific results. Predictors: collaboration; skepticism of others’ claims; questioning your own beliefs; trying to falsify hypotheses; checking citations; statistical rigor; blinded analysis; financial disclosure; open data (4) TEACHER: The regression says two ingredients are the most crucial: 1) genuine curiosity about the answer to a question, and 2) ammonium hydroxide. (5) STUDENT: Wait, why did *ammonia* score so high? How did it even get on the list? LONG HAIR: ...And now you’re doing good science!

Good Science

xkcd.com/3101/

If a seven-year-old can’t walk to the store the fault lies not with the parents but with the community.

The Neuromatch #ImpactScholars Program is a global initiative that provides early-career researchers with hands-on mentorship, collaborative project work, & next steps to grow as
computational scientists.

🤓 Berilsu Öner shares her #MyNeuromatchStory
⬇️
buff.ly/MBxDOJf

#Neuromatch #Neuroscience

Training Spiking Neural Networks Using Lessons From Deep Learning The brain is the perfect place to look for inspiration to develop more efficient neural networks. The inner workings of our synapses and neurons provide a glimpse at what the future of deep learning m...

Finally finished reading Eshraghian et al guide to training SNNs, and wow. It's one of those review papers that feel so generous. Full of insights that could each generate entire research programmes, but rather than hoarding, they shared it with us all.

arxiv.org/abs/2109.12894

Would it hurt people in tech to go and *talk* to someone with a degree in education? Most people don't understand what schools do. TL;DR: it's a lot more than info dumping into student's heads and it is certainly a lot more than daycare.

It's just one dude's house that he's done this crazy art around, but it's definitely worth a quick visit.

Phipps conservatory is also always nice.

Randyland randyland.club

Was at a conference dinner a while back and one guy said "The future is AI. It doesn't replace senior developers, but no more need for juniors."

To which i replied:

"Where do you think senior developers come from. Straight from the womb?"

He went quiet, then wandered off to a different huddle.

Bring physical buttons back on absolutely everything. Clicking, snapping, tactile friction. Chunky single-purpose electronics. Retreat from the gesture-based app-connected hellworld of the 2010s into the warm sensory embrace of the retrofuture 1980s

One weird trick for better diffusion models: concatenate some DINOv2 features to your latent channels!

Combining latents with PCA components extracted from DINOv2 features yields faster training and better samples. Also enables a new guidance strategy. Simple and effective!

Today I was able to have an LLM generate a midi bass line, have it loop that on my synth via MCP, and then jam on that on my drum kit. This is the start of something exciting

As long as universities continue to have their main role be "ticket to middle class," it'd be insane to expect them to serve classical liberal education functions. It's too late, but I think things would be a lot better if job-prep and preserving the Great Conversation were separate institutions.

1. LLM-generated code tries to run code from online software packages. Which is normal but
2. The packages don’t exist. Which would normally cause an error but
3. Nefarious people have made malware under the package names that LLMs make up most often. So
4. Now the LLM code points to malware.

Evaluation or Valuation The infinite regress of evaluating large language models

It turns out to be hard to evaluate natural language with natural language. What should we take away from the conundrum of LLM evaluation? www.argmin.net/p/evaluation...

Good presentation that makes sense of a messy research landscape.

This Github ticket is the kind of proposal that inexperienced engineers tend to make, because they think it's about code, and not about the humans who use the system.

In any competent organization, these junior folks would get some very direct feedback and it would be a growth moment.

Stop everything you are doing and review the best Open Data chart you will see all year.

Credit: @nkgarg.bsky.social's lab

We went through this in the 2010s. The Turing Test is a thought experiment for Turing to grapple with the fact that no one could define “intelligence” so he tried to operationalize it and gave the Imitation Game as as example. It was never meant to be conducted. The method is under-controlled.

20 years ago, Nine Inch Nails “The Hand That Feeds,” the first music video I directed. To celebrate this anniversary, I have constructed this immersive 2005 simulator to transport you to an authentic media viewing experience of the distant past.

Accepting “the bitter lesson” and embracing the brain’s complexity by Dyer and Richards. Great article! www.thetransmitter.org/neuroai/acce...

This is fun - training NNs using only biases works well!

Rivulet is a language that prioritizes flow. Its script was influenced by mazes, space-filling algorithms, Anni Albers' Meander series, calligraphy-friendly conlangs and natlangs

This program calculates the first set of Fibonacci numbers, stopping at 21.

It can be found at github.com/rottytoot...

A friend pointed out that the quasi-religious way so many tech guys talk about AI is in part because they don't want to grapple with the guilt of what they do; AI is a God, AI will fix it. No need to be responsible for what you put in the world.

I can't stop thinking about that.

Crowd of science supporters in Schenley Plaza

Great crowd in Pittsburgh to #standupforscience2025

Improving Retrieval and RAG with Embedding Model Finetuning Fine-tune embedding models on Databricks to enhance retrieval and RAG accuracy with synthetic data—no manual labeling required.

We're probably a little too obsessed with zero-shot retrieval. If you have documents (you do), then you can generate synthetic data, and finetune your embedding. Blog post lead by @jacobianneuro.bsky.social shows how well this works in practice.

www.databricks.com/blog/improvi...

Or it's a superposition of all of the above that collapses according to whatever state the company is in at the time

James Webb Satellite took a fantastic shot of the Planet Saturn with it's Near Infrared Camera (NIRCam) and the Mid-Infrared Instrument (MIRI). This is just an Amazing shot that shows the planet and the rings in brilliant detail.

Applications are now open! 3-week courses: Comp Neuro and Deep Learning. 2-week courses: NeuroAI and Comp Tools for Climate Science.

🚨 Neuromatch Academy Course Applications are OPEN for 2025!! 🚨

Get your application in early to be a student or teaching assistant for this year’s courses!

Applications are due Sunday, March 23.

Apply & learn more: neuromatch.io/courses/

#mlsky #compneurosky #ai #climatesolutions #ScienceEdu 🧪