Neil Traft

Portraying micro life This video is a compilation of movies of microorganisms I've made the past decade. In 2023 it was 300 years ago that the father of microscopy Antoni van Leeuwenhoek…

Happy New Year! Here's some microorganism porn. vimeo.com/1024357218

(srsly though. it's mesmerizing.)

claude code is fucking insane

i know literally NOTHING about Hegel. ZERO. and it just built me a complete system of German idealism

Fascinating story:
1. Fear-mongering about peanut allergies multiplies in the late 90s.
2. AAUP advises "no peanuts til age 3", despite NO evidence.
3. This advice CAUSES a massive spike in peanut allergies!
4. They had to do a large study just to undo the damage & convince everyone it was safe!

Astonishing: the default behavior of Chrome's "Listen to this page" feature is NOT to simply read you the page, LIKE YOU WOULD EXPECT, but instead to make one of those goofy NotebookLM AI podcasts... and I had to search the Help docs to figure out how to change it. Thanks, Google.

MAORL (Multi-Agent Olof RL)
arxiv.org/abs/2512.16705

Gov't labs can't say "climate change" in papers, "climate security" is allowed.

Maybe those planes that drop sensors into the hurricane can be "cyclone bombers", forecasting is "climate AI", and cap & trade should be called "CarbonCoin". All key tools in the "War on Climate".

This is a travesty!!

Also I have questions... for the branches that aren't terminated, where will they move? Will they be in the same building, under a different name? In which case, will it all be functionally the same thing (but with lots of political disruption)?

Counterpoint: it's the only place where I can actually reliably see posts from people I personally know. (But this may just be due to the low volume of posts... ?)

From David Krakauer's introduction to the Foundational Papers in Complexity Science. www.foundationalpapersincomplexityscience.org

Random observation: did you know this?!

I knew about how Einstein's general relativity is required to make GPS navigation work, but I'm not as familiar with how quantum mechanics factors into semiconductor technology. Remarkable.

Excellent framing(s)! A lot to think about here.

The knowledge is actually the far more valuable product. But we have trouble funding that on its own. It piggybacks on the funding of new tech inventions. If AI can invent new tech without teaching us, we stop investing in furthering our knowledge, which will ultimately lead to stagnation.

I think you're on the right track, but it doesn't even need to be so philosophical—

Current AI4Science is all about *prediction* without *understanding*. This erodes the implicit contract currently in place, where society pays for new products, and they get knowledge as a byproduct.

That's why I appreciate @togelius.bsky.social for raising this point. It's really hard for dissenting voices to speak up in that environment. Even though his argument seems to have sown a lot of confusion.

I disagree that fully-automated solutions are superior. This is an assumption, not a given.

Jeff Bezos Creates A.I. Start-Up Where He Will Be Co-Chief Executive

In applying AI to material science, biology, etc, capitalism is trying to shed science.

The point is to substitute the engineering of a machine that can generate what science has hitherto done, but without having people know things. Knowledge ultimately residing in private property is the dream.

[In considering candidates] "I actually view publication volume completely negatively... I've learned, from experience, that those with a really high volume [don't have a depth of knowledge]." —@abeirami.bsky.social

#slowscience FTW

I thought this was a fascinating way to motivate model merging: to be able to *interpolate* between model classes, rather than be forced into discrete choices. (models trained on different datasets, models of different sizes, etc.)

"Interpolation and alignment are two sides of the same coin."

Did you know that you could create hybrids across different neural net architectures—*without* updating the weights??

Come check out my poster at the UniReps @unireps.bsky.social workshop at 3:45pm today at #NeurIPS! (Or you can already browse the posters on the wall in 20D throughout the day.) 😃

Join us this Saturday at @neuripsconf.bsky.social 2025 for the @unireps.bsky.social Workshop.

Me, at people with #NeurIPS badges who aren't hurrying frantically: "Don't they know that Rich Sutton is speaking IMMINENTLY??? 😨"

Me, at people with #NeurIPS badges walking away from the convention center right now: "Don't they know that Rich Sutton is speaking in 10 minutes??? 😨"

FWIW mine has the same ones, and I am going to both of those. 🤷🏻‍♂️ Also has a grad hat which presumably refers to my student registration.

🔵🔴 Join us for the UniReps Workshop: Unifying Representations in Neural Models at
@neuripsconf.bsky.social 2025!

📍 Ballroom 20D, San Diego Convention Center
Dec 6
Don’t forget to fill out the participation form. Joining in person or remotely? We welcome your questions for the panel.
🔗 unireps.org

Link to the full paper: openreview.net/pdf?id=e4wKQ...

I think there's a lot of very interesting potential applications of "model stitching". Have a look. Plus, you get to feel like a mad scientist. IT'S ALIVE!

List of topics for the UniReps workshop.

I’ll have a poster at @unireps.bsky.social 🔵🔴 It’s a terrific workshop at the intersection of neuroscience and DL: across both biological and artificial NNs, how can we measure / compare / align / merge neural representations? Should be fascinating! Check it out if you're around! unireps.org/2025

Abstract for the paper, "Bridging Large Gaps in Neural Network Representations with Model Stitching".

So stoked to be going to my first #NeurIPS!! It’s crazy that in 10+ years of robotics and AI, I've never been to the great Lollapalooza of Machine Learning. 🥳🎆

I’m presenting my Frankensteinian efforts to stitch together parts of different neural networks! 🧪

What is imagination or daydream in this framework? What is happening when I imagine a cup?

Check out our new work on using low-rank perturbations to make evolution strategies work for billion-parameter models.

The UniReps Workshop accepted papers are out! 🎉
Huge thanks to the authors, reviewers, and incredible AC committee for their dedication and effort in making this happen. 🙏 openreview.net/group?id=Neu...

What if instead of buying software from a store, you could grow it in your garden?