{"id":13342,"date":"2022-04-20T17:38:28","date_gmt":"2022-04-21T00:38:28","guid":{"rendered":"https:\/\/worldcampaign.net\/?p=13342"},"modified":"2022-04-29T05:19:53","modified_gmt":"2022-04-29T12:19:53","slug":"message-of-the-day-huamn-rights-personal-growth","status":"publish","type":"post","link":"https:\/\/worldcampaign.net\/?p=13342","title":{"rendered":"Message of the Day: Human Rights, Personal Growth"},"content":{"rendered":"

\"\"\"\"\"\"<\/p>\n

A.I. is mastering language. Should We Trust What It Says?<\/em>, The New York Times Magazines, April 17, 2022<\/span><\/p>\n

 <\/p>\n

In 1968, a lot of history-changing things happened that resonate still.<\/p>\n

One was the impact of a movie–Stanley Kubrick’s masterwork, 2001: A Space Odyssey<\/em>.<\/p>\n

One of the unforgetbale impacts was experiencing a machine becoming human (kind of), and taking over.<\/p>\n

This aspect of the (iconic in many ways) movie is noted as a pop-icon reference to a most serious issue in another masterwork, an article in last Sundays’ New York Times Magazine.<\/p>\n

It’s an issue written about and talked about and hyped and everythinged more and more–for good reason–artifical intelligence, or AI.<\/p>\n

Here’s one quote from this feature length read:<\/p>\n

In late 2014, Stephen Hawking announced to the BBC<\/a> that \u2018\u2018the development of full artificial intelligence could spell the end of the human race.\u2019\u2019<\/em><\/p>\n

We can’t out-do that for an attention getter.<\/p>\n

Read the article, or you will wake up one day and have no idea what is or is not reality–and all that flows from that.<\/p>\n

Here it is:<\/p>\n

A.I. Is Mastering Language. Should We Trust What It Says?<\/a><\/p>\n

By <\/span>Steven Johnson,\u00a0<\/span>Artwork by <\/span>Nikita Iziev, April 17, 2022, The New Oak Times Magazine<\/span><\/p>\n

\n
\n
\n
\n
\n
\n
\n
\n

OpenAI\u2019s GPT-3 and other neural nets can now write original prose with mind-boggling fluency \u2014 a development that could have profound implications for the future.<\/em><\/p>\n

You are sitting in a comfortable chair by the fire, on a cold winter\u2019s night. Perhaps you have a mug of tea in hand, perhaps something stronger. You open a magazine to an article you\u2019ve been meaning to read. The title suggested a story about a promising \u2014 but also potentially dangerous \u2014 new technology on the cusp of becoming mainstream, and after reading only a few sentences, you find yourself pulled into the story. A revolution is coming in machine intelligence, the author argues, and we need, as a society, to get better at anticipating its consequences. But then the strangest thing happens: You notice that the writer has, seemingly deliberately, omitted the very last word of the first .<\/p>\n

The missing word jumps into your consciousness almost unbidden: \u2018\u2018the very last word of the first paragraph.\u2019\u2019<\/em> There\u2019s no sense of an internal search query in your mind; the word \u2018\u2018paragraph\u2019\u2019 just pops out. It might seem like second nature, this filling-in-the-blank exercise, but doing it makes you think of the embedded layers of knowledge behind the thought. You need a command of the spelling and syntactic patterns of English; you need to understand not just the dictionary definitions of words but also the ways they relate to one another; you have to be familiar enough with the high standards of magazine publishing to assume that the missing word is not just a typo, and that editors are generally loath to omit key words in published pieces unless the author is trying to be clever \u2014 perhaps trying to use the missing word to make a point about your<\/em>cleverness, how swiftly a human speaker of English can conjure just the right word.<\/p>\n

Siri and Alexa popularized the experience of conversing with machines, but this was on the next level, approaching a fluency that resembled science fiction.<\/strong><\/span><\/p>\n

Before you can pursue that idea further, you\u2019re back into the article, where you find the author has taken you to a building complex in suburban Iowa. Inside one of the buildings lies a wonder of modern technology: 285,000 CPU cores yoked together into one giant supercomputer, powered by solar arrays and cooled by industrial fans. The machines never sleep: Every second of every day, they churn through innumerable calculations, using state-of-the-art techniques in machine intelligence that go by names like \u2018\u2018stochastic gradient descent\u2019\u2019 and \u2018\u2018convolutional neural networks.\u2019\u2019 The whole system is believed to be one of the most powerful supercomputers on the planet.<\/p>\n

The supercomputer complex<\/strong> in Iowa is running a program created by OpenAI, an organization established in late 2015 by a handful of Silicon Valley luminaries, including Elon Musk; Greg Brockman, who until recently had been chief technology officer of the e-payment juggernaut Stripe; and Sam Altman, at the time the president of the start-up incubator Y Combinator. In its first few years, as it built up its programming brain trust, OpenAI\u2019s technical achievements were mostly overshadowed by the star power of its founders. But that changed in summer 2020, when OpenAI began offering limited access to a new program called Generative Pre-Trained Transformer 3, colloquially referred to as GPT-3. Though the platform was initially available to only a small handful of developers, examples of GPT-3\u2019s uncanny prowess with language \u2014 and at least the illusion of cognition \u2014 began to circulate across the web and through social media. Siri and Alexa had popularized the experience of conversing with machines, but this was on the next level, approaching a fluency that resembled creations from science fiction like HAL 9000 from \u201c2001\u201d: a computer program that can answer open-ended complex questions in perfectly composed sentences.<\/p>\n

As a field, A.I. is currently fragmented among a number of different approaches, targeting different kinds of problems. Some systems are optimized for problems that involve moving through physical space, as in self-driving cars or robotics; others categorize photos for you, identifying familiar faces or pets or vacation activities. Some forms of A.I. \u2014 like AlphaFold, a project of the Alphabet (formerly Google) subsidiary DeepMind \u2014 are starting to tackle complex scientific problems, like predicting the structure of proteins, which is central to drug design and discovery. Many of these experiments share an underlying approach known as \u2018\u2018deep learning,\u2019\u2019 in which a neural net vaguely modeled after the structure of the human brain learns to identify patterns or solve problems through endlessly repeated cycles of trial and error, strengthening neural connections and weakening others through a process known as training. The \u2018\u2018depth\u2019\u2019 of deep learning refers to multiple layers of artificial neurons in the neural net, layers that correspond to higher and higher levels of abstraction: In a vision-based model, for instance, a layer of neurons might detect vertical lines, which would then feed into a layer detecting edges of physical structures, which would then report to a layer that identified houses as opposed to apartment buildings.<\/p>\n

GPT-3 belongs to a category of deep learning known as a large language model, a complex neural net that has been trained on a titanic data set of text: in GPT-3\u2019s case, roughly 700 gigabytes of data drawn from across the web, including Wikipedia, supplemented with a large collection of text from digitized books. GPT-3 is the most celebrated of the large language models, and the most publicly available, but Google, Meta (formerly known as Facebook) and DeepMind have all developed their own L.L.M.s in recent years. Advances in computational power \u2014 and new mathematical techniques \u2014 have enabled L.L.M.s of GPT-3\u2019s vintage to ingest far larger data sets than their predecessors, and employ much deeper layers of artificial neurons for their training.<\/p>\n

Chances are you have already interacted with a large language model if you\u2019ve ever used an application \u2014 like Gmail \u2014 that includes an autocomplete feature, gently prompting you with the word \u2018\u2018attend\u2019\u2019 after you type the sentence \u2018\u2018Sadly I won\u2019t be able to\u2026.\u2019\u2019 But autocomplete is only the most rudimentary expression of what software like GPT-3 is capable of. It turns out that with enough training data and sufficiently deep neural nets, large language models can display remarkable skill if you ask them not just to fill in the missing word, but also to continue on writing whole paragraphs in the style of the initial prompt. For example, when I gave GPT-3 the prompt:<\/p>\n

In 1958, Frank Rosenblatt introduced the Perceptron, an early version of a neural net that could only detect the location of a square on a printed card. Fifty years later, neural nets are capable of .\u2009.\u2009.<\/em><\/strong><\/p>\n

The software dutifully completed the thought, and then continued on, picking up on the historical framing of the initial text:<\/p>\n

.\u2009.\u2009. detecting and classifying faces, finding patterns in data, and emulating the human brain. While the neural net matured in academia, it also found its way into the tech industry. In the late 1980s and early 90s, neural nets were used in speech recognition and character recognition applications. The growth in computing power and the ability to collect larger data sets allowed other neural net applications to emerge.<\/em><\/strong><\/p>\n

Since GPT-3\u2019s release, the internet has been awash with examples of the software\u2019s eerie facility with language \u2014 along with its blind spots and foibles and other more sinister tendencies. GPT-3 has been trained to write Hollywood scripts and compose nonfiction in the style of Gay Talese\u2019s New Journalism classic \u2018\u2018Frank Sinatra Has a Cold.\u2019\u2019 You can employ GPT-3 as a simulated dungeon master, conducting elaborate text-based adventures through worlds that are invented on the fly by the neural net. Others have fed the software prompts that generate patently offensive or delusional responses, showcasing the limitations of the model and its potential for harm if adopted widely in its current state.<\/p>\n

So far, the experiments with large language models have been mostly that: experiments probing the model for signs of true intelligence, exploring its creative uses, exposing its biases. But the ultimate commercial potential is enormous. If the existing trajectory continues, software like GPT-3 could revolutionize how we search for information in the next few years. Today, if you have a complicated question about something \u2014 how to set up your home theater system, say, or what the options are for creating a 529 education fund for your children \u2014 you most likely type a few keywords into Google and then scan through a list of links or suggested videos on YouTube, skimming through everything to get to the exact information you seek. (Needless to say, you wouldn\u2019t even think of asking Siri or Alexa to walk you through something this complex.) But if the GPT-3 true believers are correct, in the near future you\u2019ll just ask an L.L.M. the question and get the answer fed back to you, cogently and accurately. Customer service could be utterly transformed: Any company with a product that currently requires a human tech-support team might be able to train an L.L.M. to replace them<\/p>\n<\/div>\n<\/div>\n<\/div>\n<\/section>\n<\/header>\n<\/div>\n

\n
\n
\n
\n
\n
The text in these illustrations was generated by OpenAI\u2019s GPT-3 neural net.<\/div>\n<\/div>\n<\/div>\n
\n
\n

And those jobs might not be the only ones lost. For decades now, prognosticators have worried about the threat that A.I. and robotics pose to assembly-line workers, but GPT-3\u2019s recent track record suggests that other, more elite professions may be ripe for disruption. A few months after GPT-3 went online, the OpenAI team discovered that the neural net had developed surprisingly effective skills at writing computer software, even though the training data had not deliberately included examples of code. It turned out that the web is filled with countless pages that include examples of computer programming, accompanied by descriptions of what the code is designed to do; from those elemental clues, GPT-3 effectively taught itself how to program. (OpenAI refined those embryonic coding skills with more targeted training, and now offers an interface called Codex that generates structured code in a dozen programming languages in response to natural-language instructions.) The same principle applies to other fields that involve highly structured documents. For instance, even without the kind of targeted training that OpenAI employed to create Codex, GPT-3 can already generate sophisticated legal documents, like licensing agreements or leases.<\/p>\n<\/div>\n<\/div>\n<\/div>\n

\n
\n
\n

But as GPT-3\u2019s fluency has dazzled many observers, the large-language-model approach has also attracted significant criticism over the last few years. Some skeptics argue that the software is capable only of blind mimicry \u2014 that it\u2019s imitating the syntactic patterns of human language but is incapable of generating its own ideas or making complex decisions, a fundamental limitation that will keep the L.L.M. approach from ever maturing into anything resembling human intelligence. For these critics, GPT-3 is just the latest shiny object in a long history of A.I. hype, channeling research dollars and attention into what will ultimately prove to be a dead end, keeping other promising approaches from maturing. Other critics believe that software like GPT-3 will forever remain compromised by the biases and propaganda and misinformation in the data it has been trained on, meaning that using it for anything more than parlor tricks will always be irresponsible.<\/p>\n

Wherever you land in this debate, the pace of recent improvement in large language models makes it hard to imagine that they won\u2019t be deployed commercially in the coming years. And that raises the question of exactly how they \u2014 and, for that matter, the other headlong advances of A.I. \u2014 should be unleashed on the world. In the rise of Facebook and Google, we have seen how dominance in a new realm of technology can quickly lead to astonishing power over society, and A.I. threatens to be even more transformative than social media in its ultimate effects. What is the right kind of organization to build and own something of such scale and ambition, with such promise and such potential for abuse?<\/p>\n

Or should we be building it at all?<\/p>\n

OpenAI\u2019s origins<\/strong> date to July 2015, when a small group of tech-world luminaries gathered for a private dinner at the Rosewood Hotel on Sand Hill Road, the symbolic heart of Silicon Valley. The dinner took place amid two recent developments in the technology world, one positive and one more troubling. On the one hand, radical advances in computational power \u2014 and some new breakthroughs in the design of neural nets \u2014 had created a palpable sense of excitement in the field of machine learning; there was a sense that the long \u2018\u2018A.I. winter,\u2019\u2019 the decades in which the field failed to live up to its early hype, was finally beginning to thaw. A group at the University of Toronto had trained a program called AlexNet to identify classes of objects in photographs (dogs, castles, tractors, tables) with a level of accuracy far higher than any neural net had previously achieved. Google quickly swooped in to hire the AlexNet creators, while simultaneously acquiring DeepMind and starting an initiative of its own called Google Brain. The mainstream adoption of intelligent assistants like Siri and Alexa demonstrated that even scripted agents could be breakout consumer hits.<\/p>\n

\n
\n
\n
\n