> But maybe a better question is: “What are we going to do with these detectors now that we have them?” A lot of the people doing this research are at Google and Facebook.I guess at least we know the technology is in good hands and definitely won’t be used to harvest your personal information and sell it to.... wait, you’re saying that’s exactly what it will be used for?? Oh.

> Well the other people heavily funding vision research are the military and they’ve never done anything horrible like killing lots of people with new technology oh wait.....

> The author is funded by the Office of Naval Research and Google.

He's being funded for this. This is fantastic.

https://pjreddie.com/darknet/yolo/

https://pjreddie.com/static/Redmon%20Resume.pdf

This is the kind of guy I'd love to hang out with.

That resume is something else.

i'm all for adding an artistic flare to set your resume apart from others... but that's a bold move, cotton.

It's not about trying to catch attention, it's saying "I'm so good that even though this is totally unprofessional you're still going to want me"

It's the resume equivalent of Culture ships with silly names/AI personas.

At a certain level, it's boring to just be good. The interesting challenge becomes to stay good while being silly as fuck.

And that's why I'm serious and professional.

...you're going to want me...kept away from others due to HR cringing at my presence.

You're not filtering him out of the hiring pool, he's filtering you. ;)

Yeah, my own resume isn't (or wasn't, it has been years since i updated it) that flair-y, but it does have a sidebar with screenshots of stuff i worked on (with my face doing a weird look at the top) and is in mostly prose style with bold text for each of the projects i worked on (bold helps to scan for stuff, at least that was the idea). I've been told a few times (by friends) that this isn't how resumes are supposed to look like but my line of thinking is that if you are so stuck up that you want a specific format for a resume, then you're most likely too stuck up for me to want to work with you :-P.

My team is in a full-on hiring spree right now. I've opted out of it because there's no process.

Ultimately, it boils down to people's gut feelings, which is so disgustingly random.

The real WTF is: Apparently there is a place called "Unalaska" in Alaska!

My understanding is that the in the local language "Alaska" means "Peninsula," and "Unalaska" means "Near the peninsula."

Thats swell, we don't think about you at all.

I was reading it and kind of interested, and thought this line was funny:

> I have a lot of hope that most of the people using computer vision are just doing happy, good stuff with it, like [...] tracking their cat as it wanders around their house

And then suddenly realized I've wanted to do exactly that for a long time. Well... specifically install a camera that can detect my cat on the counter (and not my hands doing stuff) and sound an alarm/puff air to get him off.

Could this work for that? I think it could! I know my winter project...

On the topic of cats vs automation, I'd recommend reading this post [1] describing the arms race created by the writer's cat attempting to break into an automated feeding machine. HN discussion here [2]

[1] http://quinndunki.com/blondihacks/?p=3023 [2] https://news.ycombinator.com/item?id=13230904

We had an automated feeder with two chambers, each held down by a rotating, ticking timer switch. You rotate the switch to, say, 12 hours in the future, and 12 hours later the slot lines up and the lid pops over.

After many months, my cat learned to stand on top of the lid and use both paws to rotate the switch forward until the lid popped open.

This blew my mind. The switch was separated from the lid. I could imagine the cat attacking the lid itself, but this separate mechanism, requiring a motion completely distinct from the motion of an opening lid, and requiring patience without instantaneous reward or even evidence that it was going to work.... I just couldn't believe it.

Never underestimate captive animals (or humans). They have nothing but time to observe your patterns of behavior and learn from them...

There are few tech stories I enjoy more than the back-and-forth of breaking and improving a thing. A story where one side of the conflict is a cat means this might be my new favorite!

I've had good luck using low tech puzzle feeders with my cats. Each one is a bowl with a maze inside or a tower with various windows and trap doors they need to work the food out of to be able to eat. As the food levels get lower the pieces get harder to reach, which allows their laziness to take over and stop them from eating too much.

One example: https://sep.yimg.com/ay/entirelypets/kyjen-dog-games-slo-bow...

I love how he just randomly carries on his own internal dialog in his writing as if he really just doesn't give a fuck who's reading it. Totally brilliant!

I really like his licensing model, specially the META license: https://github.com/pjreddie/darknet/blob/master/LICENSE.meta

> 4. Things We Tried That Didn’t Work

I love seeing a section like this when reviewing a paper. I really wish more authors would include one. (Goodness knows I've chased down enough dead-ends in some of my own research efforts.)

Yeah, it's fun, but, seriously, git log is messy AF. I wouldn't appreciate it a bit, if somebody would do that to a project I'm involved in.

What's funny, though, the paper (written in a pretty much the same "fuck you" manner) is much more readable and informative than the average. Which says a lot about science papers out there.

Number 2 might be the greatest technical paper I've ever read. Brilliant :D