Nerdy scavenger hunt: who wants to play?

Over the past few weeks, keen-witted fans of flosser emeritus John Green's vlog -- they call themselves nerdfighters -- have been consumed with a mind-bending scavenger hunt, the clues to which have been hidden both in the real world and on the internet. And I felt that it was high time we flossers jumped into the fray, because frankly, we could give those nerdfighters a run for their money and win this thing! To do that, however, I first have to catch you up on what's been going on up to now in My Pants (aka, the Brotherhood 2.0 forum, where the nerdfighters feverishly collude to solve each clue as they come along).

So far, there have been fourteen clues. Last week, Hank (the other half of Brotherhood 2.0) posted a quick synopsis of the first nine clues, and left a tenth:

Just to give you a sense of the clues so far, here's that sixth clue that Hank refers to, which I created:

This led to a DHL box outside a Bank of America on Santa Monica Blvd. in LA, behind which there was an envelope, inside of which there was a strange image and an anagram.

The next few clues were more anagrams, which the nerdfighters deftly decoded.

Clue #12 came at the end of John's vlog on 11/13, when he said "Nerdfighters, your clue is 'Winner, South Dakota.'" This led the scavenger hunters to an earlier video, posted months before, in which John talked about the town of Winner, South Dakota, and its Wikipedia entry. In the history page of that Wikipedia entry, John had written "Look on Guilford High Street in front of the Holy Trinity Church; taped to the back of a red phone box."

Sure enough, Nerdfighters in Guildford, England found a dollar bill taped to a phone box with another anagram on it, and when that was solved, John posted a vlog in which he features several humorous venn diagrams, one of which had the number "186" written on it (subtly, I might add). Earlier that day, a user named "186" had posted a comment in one of the My Pants forums: "I like Looking for Alaska," which led hunters to the Wikipedia page for John's debut novel, and finally to a stanza from Walt Whitman's "Song of Myself," which appears to be the next clue:

Failing to fetch me at first keep encouraged,
Missing me one place search another,
I stop somewhere waiting for you.

Nerdfighter pkiverson comments "It's unclear right now whether this is a clue which is meant to lead us to a new location or new clue, or whether it is a clue meant to shed some light on the Scavenger Hunt as a whole."

Anyone got any ideas? Let's crack this thing!

Original image
iStock // Ekaterina Minaeva
Man Buys Two Metric Tons of LEGO Bricks; Sorts Them Via Machine Learning
May 21, 2017
Original image
iStock // Ekaterina Minaeva

Jacques Mattheij made a small, but awesome, mistake. He went on eBay one evening and bid on a bunch of bulk LEGO brick auctions, then went to sleep. Upon waking, he discovered that he was the high bidder on many, and was now the proud owner of two tons of LEGO bricks. (This is about 4400 pounds.) He wrote, "[L]esson 1: if you win almost all bids you are bidding too high."

Mattheij had noticed that bulk, unsorted bricks sell for something like €10/kilogram, whereas sets are roughly €40/kg and rare parts go for up to €100/kg. Much of the value of the bricks is in their sorting. If he could reduce the entropy of these bins of unsorted bricks, he could make a tidy profit. While many people do this work by hand, the problem is enormous—just the kind of challenge for a computer. Mattheij writes:

There are 38000+ shapes and there are 100+ possible shades of color (you can roughly tell how old someone is by asking them what lego colors they remember from their youth).

In the following months, Mattheij built a proof-of-concept sorting system using, of course, LEGO. He broke the problem down into a series of sub-problems (including "feeding LEGO reliably from a hopper is surprisingly hard," one of those facts of nature that will stymie even the best system design). After tinkering with the prototype at length, he expanded the system to a surprisingly complex system of conveyer belts (powered by a home treadmill), various pieces of cabinetry, and "copious quantities of crazy glue."

Here's a video showing the current system running at low speed:

The key part of the system was running the bricks past a camera paired with a computer running a neural net-based image classifier. That allows the computer (when sufficiently trained on brick images) to recognize bricks and thus categorize them by color, shape, or other parameters. Remember that as bricks pass by, they can be in any orientation, can be dirty, can even be stuck to other pieces. So having a flexible software system is key to recognizing—in a fraction of a second—what a given brick is, in order to sort it out. When a match is found, a jet of compressed air pops the piece off the conveyer belt and into a waiting bin.

After much experimentation, Mattheij rewrote the software (several times in fact) to accomplish a variety of basic tasks. At its core, the system takes images from a webcam and feeds them to a neural network to do the classification. Of course, the neural net needs to be "trained" by showing it lots of images, and telling it what those images represent. Mattheij's breakthrough was allowing the machine to effectively train itself, with guidance: Running pieces through allows the system to take its own photos, make a guess, and build on that guess. As long as Mattheij corrects the incorrect guesses, he ends up with a decent (and self-reinforcing) corpus of training data. As the machine continues running, it can rack up more training, allowing it to recognize a broad variety of pieces on the fly.

Here's another video, focusing on how the pieces move on conveyer belts (running at slow speed so puny humans can follow). You can also see the air jets in action:

In an email interview, Mattheij told Mental Floss that the system currently sorts LEGO bricks into more than 50 categories. It can also be run in a color-sorting mode to bin the parts across 12 color groups. (Thus at present you'd likely do a two-pass sort on the bricks: once for shape, then a separate pass for color.) He continues to refine the system, with a focus on making its recognition abilities faster. At some point down the line, he plans to make the software portion open source. You're on your own as far as building conveyer belts, bins, and so forth.

Check out Mattheij's writeup in two parts for more information. It starts with an overview of the story, followed up with a deep dive on the software. He's also tweeting about the project (among other things). And if you look around a bit, you'll find bulk LEGO brick auctions online—it's definitely a thing!

Original image
Name the Author Based on the Character
May 23, 2017
Original image