Sign in

Byron Galbraith

@intrinsicmode.com
196 followers 155 following 80 posts

creative machines

PostsRepliesMedia
Reposted by Byron Galbraith
Jo Wood @jwolondon.bsky.social · 15/06/2025
@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...
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                                      ╷
1257
Reposted by Byron Galbraith
Randall Munroe @xkcd.com · 12/06/2025
Good Science xkcd.com/3101/
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!
243505625
Reposted by Byron Galbraith
Popehat @kenwhite.bsky.social · 06/06/2025
If a seven-year-old can’t walk to the store the fault lies not with the parents but with the community.
1134446812
Reposted by Byron Galbraith
Neuromatch @neuromatch.bsky.social · 06/06/2025
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
021
Reposted by Byron Galbraith
Dan Goodman @neural-reckoning.org · 04/06/2025
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
arxiv.org
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...
0369
Reposted by Byron Galbraith
Mark Riedl @markriedl.bsky.social · 21/05/2025
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.
2348
Reposted by Byron Galbraith
John Bull @garius.bsky.social · 09/05/2025
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.
6340571015
Reposted by Byron Galbraith
Rob Sheridan @rob-sheridan.com · 05/05/2025
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
1618516
Reposted by Byron Galbraith
Sander Dieleman @sedielem.bsky.social · 25/04/2025
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!
0284
Byron Galbraith @intrinsicmode.com · 18/04/2025
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
020
Reposted by Byron Galbraith
Zach Weinersmith @zachweinersmith.bsky.social · 15/04/2025
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.
1414418
Reposted by Byron Galbraith
Janelle Shane @janelleshane.com · 13/04/2025
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.
12078743580
Reposted by Byron Galbraith
Ben Recht @beenwrekt.bsky.social · 10/04/2025
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...
argmin.net
Evaluation or Valuation
The infinite regress of evaluating large language models
33212
Reposted by Byron Galbraith
Mark Riedl @markriedl.bsky.social · 08/04/2025
Good presentation that makes sense of a messy research landscape.
081
Reposted by Byron Galbraith
Hilary Mason @hilarymason.com · 05/04/2025
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.
310921
Reposted by Byron Galbraith
Mor Naaman @informor.bsky.social · 02/04/2025
Stop everything you are doing and review the best Open Data chart you will see all year. Credit: @nkgarg.bsky.social's lab
2299
Reposted by Byron Galbraith
Mark Riedl @markriedl.bsky.social · 02/04/2025
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.
14714
Reposted by Byron Galbraith
Rob Sheridan @rob-sheridan.com · 28/03/2025
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.
26796185
Reposted by Byron Galbraith
Konrad Kording @kordinglab.bsky.social · 26/03/2025
Accepting “the bitter lesson” and embracing the brain’s complexity by Dyer and Richards. Great article! www.thetransmitter.org/neuroai/acce...
thetransmitter.org
» Accepting “the bitter lesson” and embracing the brain’s complexity Close menuMenuClose menuSpectrum logoYouTubeBlueskyMastodonYouTubeBlueskyMastodon
3339
Reposted by Byron Galbraith
Dan Goodman @neural-reckoning.org · 25/03/2025
This is fun - training NNs using only biases works well!
192
Reposted by Byron Galbraith
Daniel Temkin @dtemkin.bsky.social · 25/03/2025
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...
23411
Reposted by Byron Galbraith
Hilary Mason @hilarymason.com · 22/03/2025
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.
518646
Byron Galbraith @intrinsicmode.com · 07/03/2025
Great crowd in Pittsburgh to #standupforscience2025
Crowd of science supporters in Schenley Plaza
0234
Reposted by Byron Galbraith
Andrew Drozdov @mrdrozdov.com · 26/02/2025
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...
databricks.com
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.
195
Reposted by Byron Galbraith
Enigma8750 @enigma8750.bsky.social · 24/02/2025
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.
279191553100
Reposted by Byron Galbraith
Neuromatch @neuromatch.bsky.social · 24/02/2025
🚨 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 🧪
Applications are now open! 3-week courses: Comp Neuro and Deep Learning. 2-week courses: NeuroAI and Comp Tools for Climate Science.
08674
Reposted by Byron Galbraith
Anthony Michael Kreis @anthonymkreis.bsky.social · 10/02/2025
I love all my friends saying things like, “I wish I could make a career off being petty and making diss tracks” after the halftime show, and I’m out here like, “Have you considered academia?”
553998355
Reposted by Byron Galbraith
Matt Dunphy @leviathant.com · 05/02/2025
Sometimes I think about how there are worlds and cultures with depths that are impossible to fathom that you will somehow go your whole life never getting exposure to.
261
Reposted by Byron Galbraith
Nicole Carr @nicolefcarr.bsky.social · 25/01/2025
The Air Force is stripping Tuskegee Airmen lessons from basic training curriculum because of our White supremacist government. Put that in a headline. www.expressnews.com/news/article...
18840332018
Reposted by Byron Galbraith
Emily M. Bender @emilymbender.bsky.social · 25/01/2025
Apropos of a co-panelist's remarks today: If you're asking how do we get people to trust this technology, you're asking the wrong question. Should be: How do we build technology that is trustworthy & sufficiently transparent so people can make informed decisions abt when to trust it.
426861
Reposted by Byron Galbraith
The Viking (Gunnar Blohm) @gunnarblohm.bsky.social · 24/01/2025
www.nature.com/articles/s41...
nature.com
Dendrites endow artificial neural networks with accurate, robust and parameter-efficient learning - Nature Communications
Artificial neural networks, central to deep learning, are powerful but energy-consuming and prone to overfitting. The authors propose a network design inspired by biological dendrites, which offe...
16214
Reposted by Byron Galbraith
hardmaru @hardmaru.bsky.social · 24/01/2025
DeepSeek is a side project 🔥
429840
Reposted by Byron Galbraith
Dan Levenstein @dlevenstein.bsky.social · 16/01/2025
So much good history in the comments on spiking statistics and E-I balance
1154
Reposted by Byron Galbraith
The Transmitter @thetransmitter.bsky.social · 15/01/2025
Register for a neuroscience course this summer! Visit our new courses calendar to explore upcoming neuroscience courses. www.thetransmitter.org/courses/?utm...
thetransmitter.org
Courses
Explore upcoming neuroscience courses, filtered by topic.
071
Reposted by Byron Galbraith
Earl K. Miller @earlkmiller.bsky.social · 14/01/2025
Prefrontal cortex neuronal ensembles dynamically encode task features during associative memory and virtual navigation www.cell.com/cell-reports... #neuroscience
cell.com
Prefrontal cortex neuronal ensembles dynamically encode task features during associative memory and virtual navigation
Abbass et al. demonstrate that neurons in the lateral prefrontal cortex of non-human primates dynamically mix eye position and visual task features during virtual navigation. Neurons located dorsally ...
1697
Reposted by Byron Galbraith
Nine Inch Nails @nin.com · 14/01/2025
0662140
Reposted by Byron Galbraith
Nine Inch Nails @nin.com · 14/01/2025
11364204
Reposted by Byron Galbraith
Luke O'Neil @lukeoneil47.bsky.social · 12/01/2025
These fucking losers. Being bad at making music has never stopped people from making amazing music.
681847292
Reposted by Byron Galbraith
John Scalzi @scalzi.com · 12/01/2025
"AI" creative writing looks passable to people who don't look at writing all day long. To editors, it pops out like a sore thumb. LLMs are glorified predictive text machines and they predict, well, predictably. PS: if you submit an "AI" story, the editor WILL remember you, and not in a good way.
561104132
Reposted by Byron Galbraith
Mark Hamill @markhamillofficial.bsky.social · 09/01/2025
Hard to process the devastation I’ve witnessed in the last two days. Still in a state of shock for those who have lost so much in such a short period of time. #NoWords 💔
2642671866962
Reposted by Byron Galbraith
Julia Carrie Wong @joolia.bsky.social · 03/01/2025
the ai bot isn’t “admitting” its secrets to you or “revealing” its creators intentions it’s just a word generating machine generating words the only meaning is that which you read into it and imo that should be none
5851521159
Reposted by Byron Galbraith
Arvind Narayanan @randomwalker.bsky.social · 01/01/2025
Really enjoyed "Things we learned about LLMs in 2024" by @simonwillison.net, especially this analogy between today's datacenter buildout and the 19th century railway boom. The parallels are striking. simonwillison.net/2024/Dec/31/...
27815
Reposted by Byron Galbraith
Peter Murphy @peterwmurphy1.bsky.social · 01/01/2025
For Maths fans, 2025 is a square. 45² = 45 x 45 = 2025 Also, 9² x 5² = 2025 40² + 20² + 5² = 2025 My favourite? 1³+2³+3³+4³+5³+6³+7³+8³+9³ = 2025 #Mathematics #teaching #education
916248284694
Byron Galbraith @intrinsicmode.com · 01/01/2025
Happy new year! <insert cynical statements about the arbitrariness of time and the horror of existence>
020
Reposted by Byron Galbraith
Celeste Labedz @celestelabedz.bsky.social · 29/12/2024
I noticed some of these trends anecdotally early in grad school in my own dept's seminars, so I made tallies in my notes for two years. I found that "questions" to women speakers were statistically significantly more likely to be phrased as statements rather than actual questions.
924455
Reposted by Byron Galbraith
melomys @melomys.bsky.social · 28/12/2024
Not that Google was ever good, but this cartoon is a good summary of now.
8335621115
Byron Galbraith @intrinsicmode.com · 26/12/2024
Agreed-upon Gross Income
011
Reposted by Byron Galbraith
Jacob Robinson @jacobrobinson.bsky.social · 23/12/2024
What is or isn't a "BCI"? We argue in Nature BME today that if the tech stimulates or records brain activity AND does computation, it's a BCI. www.nature.com/articles/s41... But we still need a way to discuss different types of BCI separately... 🧵 #BCI #BrainComputerInterface
nature.com
An application-based taxonomy for brain–computer interfaces - Nature Biomedical Engineering
Naming brain–computer interfaces according to their intended application will assist stakeholders in the evaluation of the benefits and risks of neurotechnologies.
54716
Reposted by Byron Galbraith
kyunghyuncho.bsky.social @kyunghyuncho.bsky.social · 21/12/2024
feeling a but under the weather this week … thus an increased level of activity on social media and blog: kyunghyuncho.me/i-sensed-anx...
kyunghyuncho.me
i sensed anxiety and frustration at NeurIPS’24 – Kyunghyun Cho
1917836
Byron Galbraith @intrinsicmode.com · 17/12/2024
Ah, the memories youtu.be/KQib7LUCdDI
youtu.be
Interview with 90s Computer Nerd [Upscaled 4K]
YouTube video by Programmers are also human
030