Original image
Wikimedia Commons

The Unexpected Final Film Roles of 10 Well-Known Actors

Original image
Wikimedia Commons

Being a legend doesn’t necessarily mean you get to go out like one. Take Orson Welles, the mastermind behind Citizen Kane, who capped his big screen career as a voice in 1986’s Transformers: The Movie. Incidentally, Scatman Crothers can make the exact same claim (minus the Citizen Kane part). The point being: Neither is exactly alone in having last roles that weren’t exactly lasting roles. Take, for instance…

1. Marlon Brando – Big Bug Man (2004)

He could’ve been a contender. He made you an offer you can’t refuse. And before Brando was said and done, he was the voice of Mrs. (yes, Mrs.) Sour in this straight-to-nowhere animated feature. To help get in character, the 80-year-old Brando reportedly showed up to the one-day recording session in a blond wig, dress and make up.

2. Groucho Marx – Skidoo (1968)

Wikimedia Commons/

Speaking of preparing a role, Marx definitely walked the walk in his final film as well. Cast as “God” (a mob boss) in this gonzo drug comedy, the 80-year-old Marx went as far as to try LSD for the first time. Marx later described both the movie and his appearance in it as “God-awful.”  He reportedly enjoyed his trip a little bit more.

3. Joan Crawford – Trog (1970)

Wikimedia Commons/

In this British horror flick, the noted hater of wire hangers plays a scientist who discovers a primitive caveman and tries to domesticate him. After that, Crawford retired from acting and did some “cave dwelling” of her own, vanishing from the public eye for the last three years of her life.

4. John Belushi – Neighbors (1981)

Wikimedia Commons/Blogspot

His unhinged persona made him a legend. But Belushi couldn’t have played more against type in his final role, as a straight man opposite Dan Aykroyd’s manic turn as his obnoxious neighbor.  Unsurprisingly, they were originally cast in each other’s roles, and the last-minute switch was their idea. It was not well-received by the film’s producers … and the film wasn’t all that well-received by much of anyone.

5. Ethel Merman – Airplane! (1980)

Wikimedia Commons/

The Broadway legend last appeared on the big screen in a brief cameo, playing a wounded soldier so shell-shocked, he thinks he’s, well, Ethel Merman. Leave it to Airplane! to give someone the most meta send-off possible.

6. Ernest Borgnine – The Man Who Shook the Hand of Vicente Fernandez (2012)

Wikimedia Commons/

Here’s a truly ironic swan song: The 95-year-old Borgnine playing a dude stuck in a nursing home, wishing he’d been a famous actor. In real life, he was an Academy Award-winning actor with a varied career spanning more than six decades, stuck in a film that would end up making less money than the average orderly.

7. Jimmy Stewart – Fievel Goes West (1991)

Wikimedia Commons

For a guy who once uttered the line “Zuzu’s petals” with heartbreaking poignancy, Stewart might have been the only man alive who could’ve given any dignity to a dog sheriff named Wylie Burp.  

8. Fred Astaire – Ghost Story (1981)

Wikimedia Commons

The dancing legend played a member of the Chowder Society—a group of old men who love scary stories—in this obscure horror flick. Acting legends Douglas Fairbanks Jr., Melvyn Douglas and John Houseman played the Chowder Society’s fellow members. Only Houseman would go on to make another film. Scary!

9. Elizabeth Taylor – These Old Broads (2001)


After garnering her first and only Razzie nomination for her final film appearance (in 1994’s The Flintstones), the Oscar-winning, gossip-generating film legend quietly wound down her career on the small screen. This made her final film These Old Broads for ABC-TV in 2001. In it, a producer tries to reunite an aging, back-stabbing trio of legendary Hollywood actresses who can’t stand each other. Taylor played their agent.

10. Telly Savalas – Backfire! (1995)

Wikimedia Commons/IMDB

The “Kojak” star appeared alongside an impressive cast—including Robert Mitchum, Edie Falco, and Kathy Ireland—in this instantly-forgotten spoof of Backdraft. Telly’s role? A toilet bomber named “The Most Evil Man.”  What a way to… go.

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