Welcome to AI Weirdness!In today’s blog post, I wondered what would happen if I trained a neural net to generate numbers in the range . As you might expect, the neural net started generating numbers that were more than a little odd: 0. 9286401128496419 0. 06491227721694329 0.
9879906435756054 0. 745677946535383 0. 679450170988766 0. 1065339560745793 0. 2977483969426606 0. 05673549481890381 0.
4304206725753945 0. 7544217043730188 0. 8960721608636865 0. 7224255864247317 0. 2139997613483644 0. 0295771285597738 0.
619233475195753 0. 05578493537857566 0. 630712498931699 0. 0506476255464803 0. 3256973044703828 0.
0988207888549295 My prompt: Whales are a widely distributed and diverse group of fully aquatic placental marine mammals. They are an informal grouping within the infraorder Cetacea, usually excluding dolphins and porpoises. Whales, dolphins and porpoises belong to the order Cetartiodactyla, which consists of even toed ungulates. Their closest living relatives are the hippopotamuses, having diverged about 40 million years ago. The AI’s response: Although whales were historically thought to have descended from mesonychids, their closest living relatives are now thought to be hippopotamuses. Megaptera novaeangliae, or the humpback whale, is a species of baleen whale.
One of the largest rorqual species, adults range in length from 12–16 m and weigh about 36,000 kg. The humpback has a distinctive body shape, with long pectoral fins and a knobbly head. It is known for breaching and other distinctive surface behaviors, making it popular with whale watchers. Its diet consists mostly of krill and small fish, though it may also eat plankton, squid, and copepods. Like all large whales, the humpback was a target for the whaling industry, and once numbering in the tens of thousands, the worldwide population fell to an estimated 5,000. Orcas, also known as killer whales, are large dolphins belonging to the oceanic dolphin family, which includes the other large whales, the pilot whales and sperm whales.
Orcas are highly social; some populations are composed of matrilineal family groups which are the most stable of any animal species. Their sophisticated hunting techniques and vocal behaviors, which are often specific to a particular group and passed across generations, have been described as manifestations of culture. My prompt: “Whales are a relatively young group of mammals, having evolved from land dwelling creatures about 50 million years ago. Their terrestrial ancestors were small raccoon sized hoofed mammals, carnivorous like other ungulates of the time. Over an astonishingly quick period of time 15 million years at most, possibly less than 5 million, these land mammals made the transition to an aquatic lifestyle, gaining at first denser bones and an ear structure that allowed them to hear more easily underwater. Soon they began to look more crocodilian, their eyes migrating to the tops of their heads.
” AI’s response: Whales, and especially baleen whales, are well known for their enormous size, but most types of whales are not larger than a full grown adult human. Exceptions include the blue whale, the largest animal ever known, the extinct “Basilosaurus”, which was longer than a blue whale and likely the largest animal to have ever existed, and the “shovelnose” whales, especially the genus “Balaenoptera” which include the blue whale, “B. musculus”, the fin whale, “B. physalus”, and the sei whale, “B. borealis”. Darth Vader stood with his back to them, gloves gripping the console.
“Did you know that the blue whale is the largest animal that ever lived?” “N no, Lord Vader,” said the stormtrooper. “And yet the blue whale eats krill, which are miniscule. It can engulf up to two hundred twenty tons of water at a time. ” “I am fascinated, Lord Vader. ” The black caped Vader turned slightly toward him. “Would you like to hear more about the whales?” “Yes, Lord Vader,” came the stormtrooper’s tremulous voice.
“I would like very much to hear about the whales. ” “They can make some of the loudest and lowest sounds of any creature known. The groans of blue whales can travel thousands of kilometers through the ocean. Their calls can be heard from the surface all the way to the seafloor, some three thousand meters below the surface. You could hear the cries of a single blue whale in Tokyo and hear the answer from the one in San Francisco. ”“I see,” said the stormtrooper.
“Have you ever heard the cries of a blue whale, sergeant?”“No, Lord Vader. I have never heard the cries of a blue whale. ”“I see,” said Vader. “And have you ever seen a blue whale, sergeant?”“No, Lord Vader. I have never seen a blue whale.
”“No one has. They live too deep in the ocean. No human has ever seen a blue whale and lived to tell the tale. Until today. ”“I… I have seen a blue whale, Lord Vader?”“That is correct, sergeant.
Until today, no human has ever seen a blue whale and lived. But now you have seen one. ”“I have seen one,” said the stormtrooper, turning to face Vader, head shaking. “Yes, Lord Vader. I have seen one. I have seen a blue whale.
”A huge reason for ImageNet’s messiness is that it was automatically scraped from images on the internet. The images were supposed to have been filtered by the crowdsourced workers who labeled them, but plenty of weirdness slipped through. And horribleness many images and labels that definitely shouldn’t have appeared in a general purpose research dataset, and images that looked like they had gotten there without the consent of the people pictured. After several years of widespread use by the AI community, the ImageNet team has reportedly been removing some of that content. Other problematic datasets like those scraped from online images without permission, or from surveillance footage have been removed recently. Others, like Clearview AI’s, are still in use.
This is not just a problem with bad data, but with a system where major research groups can release datasets with such huge issues with offensive language and lack of consent. As tech ethicist Shannon Vallor put it, ”For any institution that does machine learning today, ‘we didn’t know’ isn’t an excuse, it’s a confession”. Like the algorithm that upscaled Obama into a white man, ImageNet is the product of a machine learning community where there’s a huge lack of diversity. Did you notice that most of the generated humans in this blog post are white?If you didn’t notice, that might be because so much of Western culture treats white as default. In this case, the AI might have been inadvertently rewarded for reconstructing white faces if its training data Flickr Faces HQ had a large enough skew toward white faces.
Or, as the authors of the PULSE paper pointed out in response to the conversation around bias, the standard benchmark that AI researchers use for comparing their accuracy at upscaling faces is based on the CelebA HQ dataset, which is 90% white. So even if an AI did a terrible job at upscaling other faces, but an excellent job at upscaling white faces, it could still technically qualify as state of the art. This is definitely a problem. Q: When do I use through versus threw?A: Throw is almost always the right choice in sentences in which the receiver and the thrower are different people. EXAMPLES: I threw the ball to my brother.
The receiver is different from the thrower. The burglar threw me down the stairs. The burglar is different from the receiver. The duchess threw the ball to her lady in waiting. The duchess and the lady in waiting are the same. The receiver and thrower are the same person in the sentences below.
In these cases, through is the correct word. EXAMPLES: I threw the ball through the window. The cat threw the ball through the hole. Q: How does a laser work?A: It’s simple, really. If you’ve ever seen one of those cool demos where you shine a laser through a cloud of smoke and see the smoke streak in rings, that’s all a laser is.
When you get right down to it, it’s a light beam shining through a gas, turning it into a plasma. Only instead of making the cloud of smoke glow, a laser makes it explode. What sets it apart from a regular light beam is the frequency at which it oscillates, that is to say how many times per second it is turned on and off. If you use a lower frequency you get a beam with a broader range of colors, but it will not be as focused and will have trouble with anything over a few feet. Conversely, if you use a higher frequency you’ll get a smaller range of colors and better focus, but it will lose coherency and be absorbed in the atmosphere much sooner. So what does this mean?Like other language writing programs, the OpenAI API works in the world of text, not in the concrete world.
As far as it’s concerned, there’s no real difference between sounding correct and actually being correct. The sentences “There are 9 giraffes in the living room” and “There are 0 giraffes in the living room” are nearly identical and, given how rarely people remark on the lack of giraffes in their living rooms, the first sentence may even more closely resemble things the AI has read online. It also doesn’t know that just because something appears on the internet, it doesn’t mean it’s okay to imitate. The best applications will take this into account. Other programs I’ve worked with can do this to some extent, and I’m sure we’ll be seeing more vigorous testing of this one’s capabilities against some standard benchmarks.
And not all of the API’s tweets are usable. For the dog rates tweets, around 19/20 are reasonable, and the remaining 1/20 are way off target or even contain drug references. For the janellecfakes tweets, it’s got a less consistent format to follow and maybe 1/3 are entertaining and 1/20 are plausibly something I might tweet. They’re not ready for unsupervised use. But I’m impressed with what I’ve seen so far, and will be building a lot of neat stuff with this.