Steven Walton
banner
swalton.ai
Steven Walton
@swalton.ai
Ph.D. from University of Oregon
Visiting Scholar SHI Lab @ Georgia Tech

Opinions expressed are those of my cat
Did Kohler really see Smart Pipe and go "What a great idea!"

For $600, and a monthly payment of $7, you too can send Kohler pictures of your poop!
www.kohlerhealth.com/dekoda/
www.kohlerhealth.com
October 21, 2025 at 5:30 AM
I'm not sure I'll ever learn how to type correctly on an iPhone...

The phrase I want to type is "shoot themselves in the foot"

Apple please:

1) don't correct multiple words at once. It creates more work

2) censor words or phrases. You're not protecting anyone, you're creating more harm
September 28, 2025 at 8:35 PM
Great! I always wanted to spy on my neighbors through the walls!

Seriously, I can't see how the potential for abuse doesn't significantly outweigh the utility. Abuse not only by autocrats (turnkey tyranny), but also by hackers and abusive partners.

Not cool...

news.ycombinator.com/item?id=4442...
Xfinity using WiFi signals in your house to detect motion | Hacker News
news.ycombinator.com
July 1, 2025 at 2:13 AM
My favorite #Apple thing is:

Opening a new window and it moving my workspace to that window despite my cursor being somewhere else.

e.g. Logging into a website (literally Google), getting a new popup window for my security key, popup on wrong monitor and shifts focus away just so I can move back.
June 20, 2025 at 2:06 AM
Got the #CVPR outstanding reviewer award!

There's a lot of noise in the reviewing process, so write the review you wish you received. Finding flaws is easy, but review is about the progress and making the work the best it can be. Remember, we're all on the same team.
June 13, 2025 at 10:25 PM
If you're at #CVPR, stop by Hall D from 10am-11am. I have two posters (166 & 167) I'm presenting with the eLVM Workshop.

One work on mitigating the downsides of restricted attention mechanisms, creating efficient high performance GANs. The second on the distillation of Normalizing Flows.
June 12, 2025 at 1:40 PM
You can now call me Doctor.

You don't have to, but you /can/
June 9, 2025 at 11:07 PM
People often talk about how theory and research generate little to no economic value. I'm confused by this

What's the economic value of... calculus?

Certainly an ABSURD number...
I get it. We need to make things, but you can't walk or run without the ground you stand on.
Don't take it for granted.
May 31, 2025 at 12:44 AM
Let the record show, on May 27th, 2025
GPT-o3, a model for advanced reasoning, still cannot figure out the trivial boat crossing problem without some extra help.

This came up because a discussion of how more parameters does not mean better generalization. It's the nuances that matter, that's what
May 27, 2025 at 10:59 PM
I want this (NeurIPS?), and easy navigation from the pdf to the abstract.

Google always shows the pdf but never the abstract, which has the bibtex.

Make it easy, like arxiv changing /pdf/ to /abs/

I even keep a list of urls because it's easier than regoogling

github.com/stevenwalton...
May 24, 2025 at 4:31 PM
Reposted by Steven Walton
Rereading the excellent talyarkoni.org/blog/2018/10... and thinking that perhaps what has changed is the need to win. To beat the incentives you have to be willing to not get the grant, the paper acceptance, the tenure
No, it’s not The Incentives—it’s you
There’s a narrative I find kind of troubling, but that unfortunately seems to be growing more common in science. The core idea is that the mere existence of perverse incentives is a valid and…
talyarkoni.org
April 28, 2025 at 12:12 AM
These conversations always put people into two camps:

- Those who love coding for coding's sake

- Those who love the result and code is a means to an ends

Everyone cares about the result!

So, I don't buy it. What is the divergence then?

news.ycombinator.com/item?id=4377...
The hidden cost of AI coding | Hacker News
news.ycombinator.com
April 24, 2025 at 6:17 PM
Ezra doesn't tell the full story. It's worse.

We are watching Turnkey Tyranny unfold in real time

I try not to be political on social media but were witnessing blatant violation of US law, the Constitution being undermined, and violation of international law.
April 18, 2025 at 12:30 AM
How do I know when my cat is fully charged?
April 12, 2025 at 9:53 PM
In case anyone was wondering, yes, you can transcode 8 videos to AV1 WHILE playing Elden Ring at maximum settings on a NVIDIA 4080S. I would suggest keeping it at 7 though. Little extra wiggle room.
April 5, 2025 at 5:15 AM
When someone says:

"let's start from first principles"

you can be confident the next thing they say isn't going to start from first principles.

Why is this a thing? Why is it so common in CS?
March 28, 2025 at 3:09 AM
Filling out applications to #NVIDIA and I found this in the skills section.

I didn't know they had such an interest in camping! Rest assured NVIDIA, I have the skills to survive the robot apocalypse and live in the woods! I hope it doesn't come to that, but I'm ready!
March 27, 2025 at 7:52 PM
Reposted by Steven Walton
Today's OPSEC lesson is this: all of the encryption in the world is not going to save you if you add the editor of The Atlantic to your war-planning Signal group chat.

www.theatlantic.com/politics/arc...
The Trump Administration Accidentally Texted Me Its War Plans
U.S. national-security leaders included me in a group chat about upcoming military strikes in Yemen. I didn’t think it could be real. Then the bombs started falling.
www.theatlantic.com
March 24, 2025 at 6:29 PM
I'm petty disappointed with a lot of the conversation on this Atlantic piece, especially the CNN coverage I saw.

Stop making it about using @signal.org, show how dumb they are. Let me explain.

www.theguardian.com/us-news/2025...
White House inadvertently texted top-secret Yemen war plans to journalist
In extraordinary blunder top Trump cabinet members added Atlantic editor to chat discussing strikes on Houthis
www.theguardian.com
March 25, 2025 at 1:22 AM
When you ask Siri:

"What month is it?"

This is a pretty big fail.

IME a lot of Apple ML is not highly robust. Needs more augmentation. Hopefully this isn't because lack of data harvesting (I believe it can be solved without that)

(I tried doing video but it cuts audio when talking to Siri)
March 21, 2025 at 6:31 PM
The algorithms aren't alright

How do you serve a leech who has fewer views over the official source? The problem is this seems to be the norm, not a one off.

Anyways, some cool stuff with GTC. Watch here
www.youtube.com/live/_waPvOw...
March 18, 2025 at 6:00 PM
@andrewgwils.bsky.social, you used "we" on a single author paper. You know what you have to do...
en.wikipedia.org/wiki/F._D._C...

This is a great paper and you should read it even if there is no cat coauthor.
March 17, 2025 at 10:31 PM
Every work has flaws
Every work has reason to be rejected

The purpose of review is to:
- sanity check papers, ensuring claims are reasonably evidenced
- works aren't plagiarized (i.e. "not novel").

We publish to communicate. We review to improve communication
I am somehow for the first time ever reviewing for PNAS and their reviewer instructions include this BANGER of a line:

"The purpose of peer review is not to demonstrate proficiency in identifying flaws"

Print it in eleventy point font and hang it from the hillside. Scream it from the rooftops.
March 13, 2025 at 6:58 PM
Crows are extremely intelligent animals and can learn complex behaviors.

Crows were the first to invent calculus, beating Newton by 200 years!

Crows also like food
March 13, 2025 at 6:33 PM
Reposted by Steven Walton
Love Signal. Recently got my mom on it as well.
March 12, 2025 at 10:42 PM