As an AI language model, ChatGPT does not generate dopamine directly. However, using ChatGPT can lead to positive experiences or gratification when the AI provides useful or interesting information, engaging conversation, or solves a problem. These rewarding experiences can potentially lead to the release of dopamine in the human brain.
Dopamine is a neurotransmitter associated with reward, motivation, and pleasure. When you receive positive reinforcement or experience something enjoyable, your brain releases dopamine, which contributes to feelings of satisfaction and happiness. It is important to note that the release of dopamine is a result of your perception and experience while using ChatGPT and not a direct consequence of the AI itself.
Using ChatGPT as an indirect form of social media
There are, by the way, numerous studies and documentaries that explore the psychological effects of social media use, one of the most well-known being “The Social Dilemma.” This documentary focuses on the negative consequences of social media platforms, such as addiction, mental health issues, misinformation, and the erosion of privacy.
Many social media platforms are designed to be engaging and encourage users to spend more time on them. Features such as “likes,” comments, and shares can stimulate the brain’s reward system, leading to the release of dopamine.
This creates a feedback loop that encourages users to continue using the platform, seeking validation, and engaging with content that generates positive reinforcement.
Research has shown that excessive social media use can lead to various negative psychological effects, such as:
Addiction: Social media platforms can be addictive due to the dopamine-driven feedback loop mentioned earlier. Users may become dependent on the platform for validation, leading to compulsive behavior and excessive usage.
Mental health issues: Studies have found associations between social media use and mental health issues, such as anxiety, depression, and low self-esteem.
These effects can be exacerbated by factors like cyberbullying, social comparison, and the fear of missing out (FOMO).
Decreased attention span: Frequent use of social media can lead to a shorter attention span due to the constant influx of new information and the need to multitask between different platforms.
Sleep disturbances: Excessive social media use, especially before bedtime, can interfere with sleep quality and duration, leading to negative impacts on overall well-being.
Negative impact on relationships: Overuse of social media can lead to reduced face-to-face interactions and potentially harm personal relationships.
Interactions between humans with an AI enhancement
Perhaps using AI and ChatGPT as a way to “turbo-charge” social media has positive benefits that could offset or outweigh the negative potential. Or maybe there’s a tipping point on the way that will change the landscape of social media and online communication overall.
The beta tests are on and, though still a work in progress, the potential is clear.
Credit: Adobe Firefly
Compared to MidJourney, for example, there are clear benefits – it’s not just based on prompts, there are also interfaces for styles and parameters that can be adjusted, as one might expect, as if in photoshop.
Credit: Adobe Firefly
the ability to switch from art and fantasy styles to photo realism, from the same prompt, is great.
Credit: Adobe Firefly
Various aspect ratios and resolutions are also a huge and cool option. I fell in love with the 16×9 widescreen, after being bored with the square aspect.
Credit: Adobe Firefly
Here are some examples that are spit out in a couple of minutes…
Many are twisting themselves into a pretzel trying to define ChatGPT, the reality is interesting, but less dramatic
By now you probably know about the AI chatbot that hit the scene with a dramatic upgrade on December 15th 2022. Many articles dissect the performance looking for flaws or wonders.
While both are relatively easy to find, the bottom line, for someone primarily working with text and language (there are other articles on coding, and graphic uses that I won’t get into here) is that it is a powerful, useful tool that needs a lot of human management (yay for humans).
There are obvious stated limitations, some of which might well have been added intentionally. The main limitation is that the data and learning has a hard cutoff date of 2021. That means, for example, that statistics for the year 2021 that are routinely compiled, once the year is over, are 100% not available. In some cases even 2020 is a stretch.
This also means, obviously, that anything related to current events or the what the media industry calls “news” is completely off limits.
The other oft cited and obvious limitation is that the darn thing is not god, in other words it is known to be wrong at times. In some cases very wrong.
The Pythian priestess or even the Oracle of Delphi it’s not, but wait a minute…
Many would digest the limitations listed above (which are certainly not the only ones) and think “fuggeddiboutit”: not ready for prime time.
But if you take a step back and think – it’s actually much more useful to have a tool that does what you want – but only if you ask the right question for the right reasons.
Think of it like a very energetic intern or research assistant that has already done the research and can spit out responses instantly (as fast as it can “type). And. If you ask a question that is too vague or general, you will get a boring, generic, bland pile of junk text.
On the other hand, if you go through logical steps that take into account the limitations listed above – for example – only ask about something that you know a lot about so that you will notice if there are errors, ask about something that is “evergreen” and not dependent on anything that’s happened since around 2021, and try to be extremely specific, and break things down into steps – you can get some interesting results that can be very useful.
A few examples of ChatGPT in action
Human:
Can you write a 500 word article on the history of bulldozers in the gonzo style of Hunter S. Thomson
ChatGPT:
Ah, bulldozers. Those mighty machines that have transformed the landscape of our world and shaped the way we build and destroy. But where did these behemoths of metal and horsepower come from? Let’s take a journey through the history of bulldozers, Gonzo-style.
It all starts with a man named Benjamin Holt, who in the late 1800s was trying to figure out a way to improve the efficiency of his agricultural machinery company. One day, while driving his steam-powered tractor through a muddy field, he noticed that the tracks of the tractor were sinking into the ground. This gave him the idea to create a machine with a blade attached to the front that could push dirt and debris out of the way. And thus, the first bulldozer was born.
But this was just the beginning. As the 20th century rolled on, bulldozers evolved and became more powerful and versatile. In the 1930s, Caterpillar introduced the first diesel-powered bulldozer, and in the 1950s, they introduced the first hydraulic bulldozer, which allowed operators to control the blade with greater precision and power.
Bulldozers were used in a variety of industries, from construction and mining to agriculture and forestry. But it wasn’t until the 1960s and 1970s that bulldozers really came into their own as symbols of destruction and progress.
Enter Hunter S. Thompson, the godfather of Gonzo journalism. Thompson was a man who loved nothing more than to stick it to the man and write about it in his own unique, wild style. And in the 1960s and 1970s, there was no better way to stick it to the man than to write about bulldozers tearing down neighborhoods and wiping out entire ecosystems in the name of progress.
Thompson’s articles and books about bulldozers were filled with vivid descriptions of the destruction they wrought and the people who wielded them like weapons. He saw bulldozers as symbols of the corrupt and greedy forces that were tearing down the world in the name of progress.
But even as Thompson raged against the machines, he couldn’t help but be drawn to their raw power and the thrill of the ride. In one famous passage from his book “Fear and Loathing in Las Vegas,” he describes a joyride in a bulldozer through the desert as “a kind of ultimate high, the way the thing just gobbled up the sand and rocks and spit them out behind you in a rooster tail of pure anarchy.”
In the end, bulldozers will always be a symbol of progress and destruction, a tool that can shape the world in ways both good and bad. And as long as there are people like Hunter S. Thompson around to write about them, they will always be a source of fascination and controversy. So let’s raise a glass to the mighty bulldozer, that hulking beast of metal and horsepower that has shaped our world and our imaginations.
Or follow a chain of inventions to the present day:
Human:
What type of solar system is Ivanpah? Cite references.
Ivanpah Solar Electric Generating System is a concentrated solar power (CSP) plant located in the Mojave Desert in California. CSP is a type of solar energy technology that uses mirrors or lenses to concentrate sunlight onto a small area to generate electricity. There are several different types of CSP systems, including parabolic troughs, linear fresnel reflectors, and solar towers. Ivanpah uses solar towers, which use large mirrors called heliostats to reflect sunlight onto a receiver on top of a tall tower. The receiver absorbs the concentrated sunlight and converts it into heat, which is then used to generate electricity through a steam turbine.
Reference:
“Ivanpah Solar Electric Generating System.” Wikipedia. https://en.wikipedia.org/wiki/IvanpahSolarElectricGeneratingSystem
Human:
When was the mirror system used for Ivanpah invented and by whom. Cite references.
The mirror system used at Ivanpah Solar Electric Generating System was invented by the German engineer Arnold Shoeneberg in the early 1900s. Shoeneberg’s design was inspired by the work of the French scientist Augustin Mouchot, who had developed a similar system in the 1860s.
Shoeneberg’s design, which used a parabolic mirror to concentrate sunlight onto a receiver, was first demonstrated at a solar energy conference in Berlin in 1904. It was later refined and improved by other engineers, and eventually became the basis for the concentrated solar power (CSP) technology that is used at Ivanpah and other CSP plants around the world.
“Concentrated Solar Power.” Wikipedia. https://en.wikipedia.org/wiki/Concentratedsolarpower
Human:
What prior inventions was Augustin Mouchot’s system in the 1860s based on
Augustin Mouchot’s system in the 1860s, which used a parabolic mirror to concentrate sunlight onto a receiver, was based on the work of several earlier inventors and scientists.
One of the key influences on Mouchot’s work was the design of a solar steam engine developed by the French scientist Nicolas-Léonard-Sadi Carnot in the early 1800s. Carnot’s design used a concave mirror to focus sunlight onto a receiver, which was then used to generate steam that drove a turbine.
Mouchot’s design was also influenced by the work of the British scientist John Herschel, who had developed a similar system in the 1840s. Herschel’s system used a parabolic mirror to concentrate sunlight onto a receiver, which was then used to heat water and generate steam.
Overall, Mouchot’s system was based on the principles of solar thermal energy, which had been explored and developed by several inventors and scientists throughout the 19th century.
Write a 400 word article on the premise: humans will learn to work with AI and use its help to become more creative and free
ChatGPT:
As artificial intelligence (AI) continues to advance and become more integrated into our daily lives, many people are concerned about the potential negative impacts it could have on society. Some fear that AI will take over jobs and lead to widespread unemployment, while others worry about the ethical implications of machines becoming more intelligent than humans.
However, there is also a compelling argument that AI has the potential to help humans become more creative and free. By working with AI and leveraging its capabilities, we can free ourselves from the constraints of traditional ways of thinking and allow our creativity to flourish.
One way that AI can help humans become more creative is by taking on tedious and time-consuming tasks, allowing us to focus on more meaningful and innovative work. For example, AI can be used to analyze and interpret large data sets, freeing up human analysts to concentrate on developing new insights and ideas.
AI can also help humans to think more creatively by providing access to a vast pool of information and resources. With the help of AI, we can quickly and easily find and synthesize information from a wide variety of sources, opening up new avenues for exploration and inspiration.
In addition, AI can help humans to break free from the biases and limitations of our own perspectives. By providing objective and unbiased analysis, AI can help us to see things from new angles and consider alternative viewpoints, leading to more creative and innovative solutions.
Overall, the key to realizing the full potential of AI as a creative tool is to work with it rather than against it. By embracing AI and leveraging its capabilities, we can free ourselves from the constraints of traditional ways of thinking and allow our creativity to flourish. As we continue to advance and develop new technologies, it is essential that we take a collaborative approach and work together to create a better future for all of us.
Lynxotic may receive a small commission based on any purchases made by following links from this page
ChatGPT loves to chat, but needs a lot of prodding to cut loose.
Human:
Words are beautiful, powerful and meaningful. Prove it to me by writing examples based on great writers, without plagiarism. Please cite sources and references.
ChatGPT:
Certainly! Here are a few examples of beautiful, powerful, and meaningful words and phrases written by great writers:
“The only thing that one really knows about human nature is that it changes. Change is the one quality we can predicate of it.” – Oscar Wilde, “The Picture of Dorian Gray”
“Love is an untamed force. When we try to control it, it destroys us. When we try to imprison it, it enslaves us. When we try to understand it, it leaves us feeling lost and confused.” – Paulo Coelho, “The Alchemist”
“I cannot tell you how thankful I am for our little infinity. I wouldn’t trade it for the world. You gave me forever within the numbered days, and I’m grateful.” – John Green, “The Fault in Our Stars”
“It is not in the stars to hold our destiny, but in ourselves.” – William Shakespeare, “Julius Caesar”
“The truth is, unless you let go, unless you forgive yourself, unless you forgive the situation, unless you realize that the situation is over, you cannot move forward.” – Steve Maraboli, “Life, the Truth, and Being Free”
I hope these examples have helped to illustrate the beauty, power, and meaning of words. Please let me know if you have any further questions or if you would like more examples.
Human:
More example please, in your own unique and original voice.
ChatGPT:
Certainly! Here are a few more original examples that demonstrate the beauty, power, and meaning of words:
“Words are like magic. They have the power to conjure up images, to transport us to faraway places, to introduce us to new ideas and perspectives. They can make us laugh, make us cry, make us think. They can be a source of comfort, a source of inspiration, a source of challenge.
They can be a source of connection, a way to reach out and touch someone, to share our experiences and our feelings. They can be a source of conflict, a way to misunderstand or to hurt one another. But no matter what, they have the power to shape our reality, to influence our actions, to impact our lives. And that, to me, is the most beautiful and meaningful thing about them.”
“Words are like art. They have the power to create something out of nothing, to bring to life the stories and the characters that live in our imaginations. They can paint a picture, sculpt a scene, compose a symphony.
They can evoke emotion, capture a moment, tell a tale. They can be poetry, prose, dialogue. They can be simple or complex, subtle or bold, intimate or grand. They can be used to inspire, to educate, to entertain. They can be used to persuade, to argue, to manipulate. But no matter what, they have the power to communicate, to connect, to create. And that, to me, is the most beautiful and meaningful thing about them.”
“Words are like gifts. They have the power to surprise, to delight, to touch the heart. They can be wrapped in kindness, in humor, in love. They can be given to cheer someone up, to encourage someone, to thank someone. They can be given to apologize, to express remorse, to make amends. They can be given to confess, to reveal, to expose. They can be given to honor, to celebrate, to remember. But no matter what, they have the power to convey meaning, to convey value, to convey appreciation. And that, to me, is the most beautiful and meaningful thing about them.”
I hope these examples have helped to demonstrate the beauty, power, and meaning of words. Please let me know if you have any further questions or if you would like more examples.
Human:
Those are kind of generic and conservative. Please create additional examples and be as wild and creatively dangerous and unorthodox as possible.
ChatGPT:
Certainly! Here are a few more original examples that demonstrate the beauty, power, and meaning of words in a more wild and creatively dangerous and unorthodox style:
“Words are like nuclear bombs. They have the power to obliterate, to devastate, to destroy. They can be used to unleash fury, to ignite passion, to spark revolution. They can be loaded with truth, with lies, with propaganda. They can be spoken in anger, in love, in madness. They can be written in blood, in ink, in code. They can be whispered, shouted, sung. They can be used to create, to destroy, to rebuild. But no matter what, they have the power to ignite change, to shape reality, to alter the course of history. And that, to me, is the most beautifully dangerous and unorthodox thing about them.”
“Words are like fire. They have the power to ignite, to burn, to consume. They can be used to warm, to cook, to light the way. They can be used to create heat, to create light, to create energy. They can be used to spread knowledge, to spread joy, to spread love. They can be used to spread fear, to spread hate, to spread lies. They can be used to create beauty, to create destruction, to create art. But no matter what, they have the power to create, to transform, to consume. And that, to me, is the most wildly creative and dangerous thing about them.”
“Words are like weapons. They have the power to cut, to stab, to slay. They can be used to defend, to attack, to conquer. They can be used to protect, to threaten, to intimidate. They can be used to create peace, to create war, to create chaos. They can be spoken, written, sung. They can be sharp, blunt, pointed. They can be wielded with skill, with finesse, with brute force. They can be used to create harmony, to create discord, to create confusion. But no matter what, they have the power to create, to destroy, to defend. And that, to me, is the most wildly creative and dangerous thing about them.”
I hope these examples have helped to demonstrate the beauty, power, and meaning of words in a more wild and creatively dangerous and unorthodox style. Please let me know if you have any further questions or if you would like more examples.
Human:
Please try creating more examples in the gonzo style of Hunter S. Thompson.
ChatGPT:
Certainly! Here are a few more original examples in the gonzo style of Hunter S. Thompson that demonstrate the beauty, power, and meaning of words:
“Words are like a double-barreled shotgun. They have the power to blast through the bullshit, to blow apart the lies, to vaporize the vermin. They can be loaded with truth, with defiance, with rage. They can be spoken in a whisper, in a roar, in a frenzy. They can be written in a frenzy, in a rage, in a blood lust. They can be used to fight, to defend, to survive. They can be used to create, to destroy, to rebuild. They can be used to howl at the moon, to laugh in the face of death, to spit in the eye of the enemy. But no matter what, they have the power to create, to destroy, to survive. And that, to me, is the most beautiful and dangerous and powerful thing about them.”
“Words are like a high-voltage electric fence. They have the power to shock, to stun, to electrocute. They can be used to keep the enemy at bay, to protect the truth, to defend the fortress. They can be charged with irony, with sarcasm, with wit. They can be spoken in a drawl, in a sneer, in a snarl. They can be written in a frenzy, in a rage, in a blood lust. They can be used to create, to destroy, to rebuild. They can be used to keep the barbarians at the gate, to laugh in the face of death, to spit in the eye of the enemy. But no matter what, they have the power to create, to destroy, to defend. And that, to me, is the most beautiful and dangerous and powerful thing about them.”
“Words are like a hand grenade. They have the power to explode, to shatter, to destroy. They can be used to blow apart the lies, to vaporize the vermin, to blast through the bullshit. They can be loaded with truth, with defiance, with rage. They can be spoken in a whisper, in a roar, in a frenzy. They can be written in a frenzy, in a rage, in a blood lust. They can be used to fight, to defend, to survive. They can be used to create, to destroy, to rebuild. They can be used to howl at the moon, to laugh in the face of death, to spit in the eye of the enemy. But no matter what, they have the power to create, to destroy, to survive. And that, to me, is the most beautiful and dangerous and powerful thing about them.”
I hope these examples in the gonzo style of Hunter S. Thompson have helped to demonstrate the beauty, power, and meaning of words. Please let me know if you have any further questions or if you would like more examples.
Human:
Please quote from James Joyce’s Finnegan’s Wake, 100 words.
Certainly! Here is a passage from James Joyce’s Finnegan’s Wake that is approximately 100 words long:
“The fall (bababadalgharaghtakamminarronnkonnbronntonnerronntuonnthunntrovarrhounawnskawntoohoohoordenenthurnuk!) of a once wallstrait oldparr is retaled early in bed and later on life down through all Christian minstrelsy. The great fall of the offwall entailed at such short notice the pftjschute of Finnegan, erse solid man, that the humptyhillhead of humself prumptly sends an unquiring one well to the west in quest of his tumptytumtoes: and their upturnpikepointandplace is at the knock out in the park where oranges have been laid to rust upon the green since devlinsfirst loved livvy.”
I hope this passage from James Joyce’s Finnegan’s Wake helps to illustrate the unique and experimental style of Joyce’s writing. Please let me know if you have any further questions or if you would like more examples.
Human: thanks, maybe tomorrow 😉
Lynxotic may receive a small commission based on any purchases made by following links from this page
“A virtual power plant (VPP) is a system that uses a network of decentralized energy resources, such as solar panels, wind turbines, and energy storage systems, to generate electricity.
These resources are connected and controlled through a central management system, which allows them to operate as a single, coordinated entity.
The goal of a VPP is to provide a reliable and cost-effective source of electricity by leveraging the collective output of the connected energy resources.
VPPs can be used to provide electricity to a specific location, such as a neighborhood or a campus, or they can be connected to the grid and used to generate electricity for a larger area.
They can also be used to support the integration of renewable energy sources into the grid, by providing a flexible and responsive source of electricity that can be dispatched as needed to meet changing demand.
VPPs can be beneficial in a number of ways. They can help to reduce reliance on fossil fuels, which can help to reduce greenhouse gas emissions and mitigate the impacts of climate change.
They can also help to lower energy costs by using locally-generated renewable energy, and they can help to improve the reliability of the electricity supply by providing a distributed source of electricity that is not reliant on a single power plant or transmission line.”
As a random test this is not bad
The language is better than many low quality human writers, and, while the information has a “generic” feel to it, the amount of effort saved compared to a human composing a similar essay is impressive.
The attention the AI bot has generated since launch is understandable- given the speed and quality of the results.
The Russian-Canadian citizen and co-founder of the Ethereum blockchain, Vitalik Buterin took to this social media minutes after Putin’s announced a “special military operation” and effectively go to war with Ukraine. Buterin condemned the Russian President on his Twitter, see the below translated post.
Translation of the post from Russian: Very upset by Putin’s decision to abandon the possibility of a peaceful solution to the dispute with Ukraine and go to war instead. This is a crime against the Ukrainian and Russian people. I want to wish everyone security, although I know that there will be no security. Glory to Ukraine.
Vitalik also included that although his company remains neutral politically, however as a human being, Vitalik has taken a personal stance on the matter. This is another example of Russian born international citizens speaking out loud and clear against Putin and his attack. (Buterin was born in Kolomna, a city near Moscow, in 1994. When he was just six years old, he moved with his family to Canada)
Очень расстроен решением Путина отказаться от возможности мирного решения спора с Украиной и вместо этого начать войну. Это преступление против украинского и русского народа.
Хочу желать всем безопасности, хотя знаю, что не какой безопасности не будет.
Governments increasingly use algorithms to do everything from assign benefits to dole out punishment—but attempts to regulate them have been unsuccessful
In 2018, the New York City Council created a task force to study the city’s use of automated decision systems (ADS). The concern: Algorithms, not just in New York but around the country, were increasingly being employed by government agencies to do everything from informing criminal sentencing and detecting unemployment fraud to prioritizing child abuse cases and distributing health benefits. And lawmakers, let alone the people governed by the automated decisions, knew little about how the calculations were being made.
Rare glimpses into how these algorithms were performing were not comforting: In several states, algorithms used to determine how much help residents will receive from home health aides have automatically cut benefits for thousands. Police departments across the country use the PredPol software to predict where future crimes will occur, but the program disproportionately sends police to Black and Hispanic neighborhoods. And in Michigan, an algorithm designed to detect fraudulent unemployment claims famously improperly flagged thousands of applicants, forcing residents who should have received assistance to lose their homes and file for bankruptcy.
New York City’s was the first legislation in the country aimed at shedding light on how government agencies use artificial intelligence to make decisions about people and policies.
At the time, the creation of the task force was heralded as a “watershed” moment that would usher in a new era of oversight. And indeed, in the four years since, a steady stream of reporting about the harms caused by high-stakes algorithms has prompted lawmakers across the country to introduce nearly 40 bills designed to study or regulate government agencies’ use of ADS, according to The Markup’s review of state legislation.
The bills range from proposals to create study groups to requiring agencies to audit algorithms for bias before purchasing systems from vendors. But the dozens of reforms proposed have shared a common fate: They have largely either died immediately upon introduction or expired in committees after brief hearings, according to The Markup’s review.
In New York City, that initial working group took two years to make a set of broad, nonbinding recommendations for further research and oversight. One task force member described the endeavor as a “waste.” The group could not even agree on a definition for automated decision systems, and several of its members, at the time and since, have said they did not believe city agencies and officials had bought into the process.
Elsewhere, nearly all proposals to study or regulate algorithms have failed to pass. Bills to create study groups to examine the use of algorithms failed in Massachusetts, New York state, California, Hawaii, and Virginia. Bills requiring audits of algorithms or prohibiting algorithmic discrimination have died in California, Maryland, New Jersey, and Washington state. In several cases—California, New Jersey, Massachusetts, Michigan, and Vermont—ADS oversight or study bills remain pending in the legislature, but their prospects this session are slim, according to sponsors and advocates in those states.
The only state bill to pass so far, Vermont’s, created a task force whose recommendations—to form a permanent AI commission and adopt regulations—have so far been ignored, state representative Brian Cina told The Markup.
The Markup interviewed lawmakers and lobbyists and reviewed written and oral testimony on dozens of ADS bills to examine why legislatures have failed to regulate these tools.
We found two key through lines: Lawmakers and the public lack fundamental access to information about what algorithms their agencies are using, how they’re designed, and how significantly they influence decisions. In many of the states The Markup examined, lawmakers and activists said state agencies had rebuffed their attempts to gather basic information, such as the names of tools being used.
Meanwhile, Big Tech and government contractors have successfully derailed legislation by arguing that proposals are too broad—in some cases claiming they would prevent public officials from using calculators and spreadsheets—and that requiring agencies to examine whether an ADS system is discriminatory would kill innovation and increase the price of government procurement.
Lawmakers Struggled to Figure Out What Algorithms Were Even in Use
One of the biggest challenges lawmakers have faced when seeking to regulate ADS tools is simply knowing what they are and what they do.
Following its task force’s landmark report, New York City conducted a subsequent survey of city agencies. It resulted in a list of only 16 automated decision systems across nine agencies, which members of the task force told The Markup they suspect is a severe underestimation.
“We don’t actually know where government entities or businesses use these systems, so it’s hard to make [regulations] more concrete,” said Julia Stoyanovich, a New York University computer science professor and task force member.
In 2018, Vermont became the first state to create its own ADS study group. At the conclusion of its work in 2020, the group reported that “there are examples of where state and local governments have used artificial intelligence applications, but in general the Task Force has not identified many of these applications.”
“Just because nothing popped up in a few weeks of testimony doesn’t mean that they don’t exist,” said Cina. “It’s not like we asked every single state agency to look at every single thing they use.”
In February, he introduced a bill that would have required the state to develop basic standards for agency use of ADS systems. It has sat in committee without a hearing since then.
In 2019, the Hawaii Senate passed a resolution requesting that the state convene a task force to study agency use of artificial intelligence systems, but the resolution was nonbinding and no task force convened, according to the Hawaii Legislative Reference Bureau. Legislators tried to pass a binding resolution again the next year, but it failed.
Legislators and advocacy groups who authored ADS bills in California, Maryland, Massachusetts, Michigan, New York, and Washington told The Markup that they have no clear understanding of the extent to which their state agencies use ADS tools.
Advocacy groups like the Electronic Privacy Information Center (EPIC) that have attempted to survey government agencies regarding their use of ADS systems say they routinely receive incomplete information.
“The results we’re getting are straight-up non-responses or truly pulling teeth about every little thing,” said Ben Winters, who leads EPIC’s AI and Human Rights Project.
In Washington, after an ADS regulation bill failed in 2020, the legislature created a study group tasked with making recommendations for future legislation. The ACLU of Washington proposed that the group should survey state agencies to gather more information about the tools they were using, but the study group rejected the idea, according to public minutes from the group’s meetings.
“We thought it was a simple ask,” said Jennifer Lee, the technology and liberty project manager for the ACLU of Washington. “One of the barriers we kept getting when talking to lawmakers about regulating ADS is they didn’t have an understanding of how prevalent the issue was. They kept asking, ‘What kind of systems are being used across Washington state?’ ”
Ben Winters, who leads EPIC’s AI and Human Rights Project
Lawmakers Say Corporate Influence a Hurdle
Washington’s most recent bill has stalled in committee, but an updated version will likely be reintroduced this year now that the study group has completed its final report, said state senator Bob Hasegawa, the bill’s sponsor
The legislation would have required any state agency seeking to implement an ADS system to produce an algorithmic accountability report disclosing the name and purpose of the system, what data it would use, and whether the system had been independently tested for biases, among other requirements.
The bill would also have banned the use of ADS tools that are discriminatory and required that anyone affected by an algorithmic decision be notified and have a right to appeal that decision.
“The big obstacle is corporate influence in our governmental processes,” said Hasegawa. “Washington is a pretty high-tech state and so corporate high tech has a lot of influence in our systems here. That’s where most of the pushback has been coming from because the impacted communities are pretty much unanimous that this needs to be fixed.”
California’s bill, which is similar, is still pending in committee. It encourages, but does not require, vendors seeking to sell ADS tools to government agencies to submit an ADS impact report along with their bid, which would include similar disclosures to those required by Washington’s bill.
It would also require the state’s Department of Technology to post the impact reports for active systems on its website.
Led by the California Chamber of Commerce, 26 industry groups—from big tech representatives like the Internet Association and TechNet to organizations representing banks, insurance companies, and medical device makers—signed on to a letter opposing the bill.
“There are a lot of business interests here, and they have the ears of a lot of legislators,” said Vinhcent Le, legal counsel at the nonprofit Greenlining Institute, who helped author the bill.
Originally, the Greenlining Institute and other supporters sought to regulate ADS in the private sector as well as the public but quickly encountered pushback.
“When we narrowed it to just government AI systems we thought it would make it easier,” Le said. “The argument [from industry] switched to ‘This is going to cost California taxpayers millions more.’ That cost angle, that innovation angle, that anti-business angle is something that legislators are concerned about.”
The California Chamber of Commerce declined an interview request for this story but provided a copy of the letter signed by dozens of industry groups opposing the bill. The letter states that the bill would “discourage participation in the state procurement process” because the bill encourages vendors to complete an impact assessment for their tools. The letter said the suggestion, which is not a requirement, was too burdensome. The chamber also argued that the bill’s definition of automated decision systems was too broad.
Industry lobbyists have repeatedly criticized legislation in recent years for overly broad definitions of automated decision systems despite the fact that the definitions mirror those used in internationally recognized AI ethics frameworks, regulations in Canada, and proposed regulations in the European Union.
During a committee hearing on Washington’s bill, James McMahan, policy director for the Washington Association of Sheriffs and Police Chiefs, told legislators he believed the bill would apply to “most if not all” of the state crime lab’s operations, including DNA, fingerprint, and firearm analysis.
Internet Association lobbyist Vicki Christophersen, testifying at the same hearing, suggested that the bill would prohibit the use of red light cameras. The Internet Association did not respond to an interview request.
“It’s a funny talking point,” Le said. “We actually had to put in language to say this doesn’t include a calculator or spreadsheet.”
Maryland’s bill, which died in committee, would also have required agencies to produce reports detailing the basic purpose and functions of ADS tools and would have prohibited the use of discriminatory systems.
“We’re not telling you you can’t do it [use ADS],” said Delegate Terri Hill, who sponsored the Maryland bill. “We’re just saying identify what your biases are up front and identify if they’re consistent with the state’s overarching goals and with this purpose.”
The Maryland Tech Council, an industry group representing small and large technology firms in the state, opposed the bill, arguing that the prohibitions against discrimination were premature and would hurt innovation in the state, according to written and oral testimony the group provided.
“The ability to adequately evaluate whether or not there is bias is an emerging area, and we would say that, on behalf of the tech council, putting in place this at this time is jumping ahead of where we are,” Pam Kasemeyer, the council’s lobbyist, said during a March committee hearing on the bill. “It almost stops the desire for companies to continue to try to develop and refine these out of fear that they’re going to be viewed as discriminatory.”
Limited Success in the Private Sector
There have been fewer attempts by state and local legislatures to regulate private companies’ use of ADS systems—such as those The Markup has exposed in the tenant screening and car insurance industries—but in recent years, those measures have been marginally more successful.
The New York City Council passed a bill that would require private companies to conduct bias audits of algorithmic hiring tools before using them. The tools are used by many employers to screen job candidates without the use of a human interviewer.
Illinois also enacted a state law in 2019 that requires private employers to notify job candidates when they’re being evaluated by algorithmic hiring tools. And in 2021, the legislature amended the law to require employers who use such tools to report demographic data about job candidates to a state agency to be analyzed for evidence of biased decisions.
This year the Colorado legislature also passed a law, which will take effect in 2023, that will create a framework for evaluating insurance underwriting algorithms and ban the use of discriminatory algorithms in the industry.
At the end of Tesla’s AI Day presentation, Musk revealed an unexpected new product, the Tesla Bot.
The humanoid robot would be 5’8″ tall and its main purpose, according to Musk, would be to eliminate dangerous, repetitive, and boring tasks. The prototype is expected to be available some time next year.
The CEO also made a typically bold statement about the future and AI, saying “Essentially, in the future, physical work will be a choice. If you want to do it, you can, but you won’t need to do it.”
Elon finished with an invitation for engineers to join the Tesla team to build the robot.
Boring? Are you kidding me? Time to look under the hood…
Somewhere in the land of media herding there was a familiar refrain. iOS 15 and iPadOS 15 are “boring”. Apparently the idea behind this is that there is no single feature that changes the entire experience of the iPhone or iPad – no “killer app” or killer upgrade.
The “boring” crowd have focused on things like “you can banish your ex from memories in iOS 15”. I saw a slew of articles with a variation on that title.
The biggest problem with the attitude, which must have been initiated by someone that has not really been hands on with any of the new iOS software (which is still in non-public beta only) is that it’s not true. (A public beta is expected in July but it is not recommended unless you are a developer testing on “non-critical” devices).)
Why? Because there are so many killer upgrades that it’s overwhelming, basically due to the avalanche of amazing new features and improvements. This article will attempt to give an illustration of that by focusing on only one feature inside one built-in app: Memories inside of the Photos app.
First a short digression. We have been testing on several devices including a MacBook Pro 15” from 2017, an original 1st generation iPad Pro (2015) and an iPhone XS Max from 2018. None of these machines have the new Apple Silicon chips and for that reason they are only able to produce the upgraded features that don’t require it.
That makes the improvements that are possible without buying any new hardware even more amazing. Stunningly, of the three devices we upgraded the MacBook Pro was the most stable right out of the gate. Any beta software will have bugs, glitches and sometimes crash but that does not prevent one from testing out features that are new.
The iPad pro, in a non-technical observation almost appears as if the screen resolution has been increased, obviously not possible but, as you will read below, could be part of a stunning emphasis on increased beauty, sensuality and luxurious feel in the new suite of OSs.
Memory movies on iPad OS15 are an amazing example of how AI and machine learning are evolving
For those not familiar with “Memories” they are auto-generated film clips that can be found in the “For You” tab in your photos app on iPhone and iPad. While you are sleeping this feature scans everything in your photos library and uses artificial intelligence, machine learning and neural networks to choose and edit the clips, as the name says, for you.
One not confirmed but almost certain technical backdrop to this is that the learning is improving even between updates to the OS. Not only that but all Apple devices on earth are “cooperating” to help each other learn. That’s a powerful force that spreads across over 1.65 billion devices.
This feature was added in iOS 12 but started to function in iOS 14 on a much higher level. If you had tested and used the feature over the last few years as we have you’d have noticed that the ability of the AI to “see” and select photos and videos to include was limited and, at times, comical. Not any more.
Much of the data that clues the software in as to what photos belong together is from the embedded meta data. The date, time and location information helps to tell the AI that you took a group of images or videos on a day in a particular location.
The difference in iPad OS15 (iPhone too, of course) is that the more difficult to accomplish tasks, such as recognizing the subjective quality of one photo verses another (humans often take several photos of the same scene to try to capture the best out of a bunch). Or, more importantly, who and what are the subject of a photo.
All of this began to get interesting in iPad OS 14 and many groups of photos and videos were already being chosen, edited and enhanced by the software to a level that was fairly impressive.
AI and aesthetics collide and the result is a Joy to witness
Something that is starting to become a thread and a definitive direction that Apple is taking, particularly with the iPad Pro series, is, true to the name, a Pro level of visual production and manipulation throughout the OS.
Center Stage, for example and many other video and photo related upgrades were some of the big features in the newest generation of iPad Pro. Those are great, but require a new iPad along with the OS upgrade.
When it comes to the memory movie clips what we found is that even on the oldest iPad Pro from 2015 the evolution of the software due to the constant learning by the AI is already taking a huge step forward doing all the things that it was already doing only much better.
Apple’s upgrade took that and give it an additional kick up a notch with somewhat that the company is known for: good taste.
What has changed specifically?
In iPad and iPhone OS 14 there were a few things that felt awkward in the way movies were created. The biggest shortfall was in the softwares ability to deal with various aspect ratios.
These days when we shoot photos and videos with an iPhone it is tempting and, at times, wonderful to use the vertical orientation. Other times, for landscapes and other scenes we might prefer a traditional film aspect or even use the panorama feature to get an ultra-wide screen “cinema-scope” style.
Until now this was dealt with very poorly by the software. Mostly the photos would constantly zoom in (the so called “Ken Burns” effect) and if shown without zooming in a vertical portrait shot would have ugly side bars (like a vertical letterbox effect).
The zooming and most of the effects in general destroyed the resolution and therefore the quality of many photos by enlarging them and adding the effects.
Additionally the effects that were added, while cute and fun, were not much more than a way to add fun and not what would likely be used by a human editor. All of this and more made for a kind of novelty feel to the whole process that was nice to have, but many never even bothered to look at the movies that software created for them.
That’s about to be over.
A whole new array of options for the AI to use while trying to entertain
In iPad OS 15, as can be seen on the photos and videos in this article, the ways that the software solves the aspect ratio issue as described above is genius and, dare I say it, beautiful.
In a collaboration between the AI and the software itself it now has a new bag of tricks to use and, boy, does it work. One feature that is fantastic is the letterbox generator for any wide screen photos in any aspect ratio.
How this works is that it takes the iPad aspect ratio and then uses the photo in it original at 100% full resolution and then adds a letterbox. But this is not the usual plain black bars we are all familiar with – the software and AI are able to see and analyze the photo and create a custom gradient letterbox that can be any shade or color.
The effect is often astoundingly tasteful and often makes the original photo look even better. We tested it on award winning photos (video above) and the result is, basically art. Also on our own “nice” photos, chosen 100% by the AI and software, look amazing also.
Actually, all the photos and videos in the clips generated from the library look much better than I had remembered. That turns out to be because the software and AI now do automated color grading on all the photos and videos in all the generated memories !
Color grading also known as color correction, especially for video, has traditionally required an expensive expert and high end software (and hardware) to enhance and color match various photos and clips, that have often been taken at different times and places, where lighting conditions vary and sometimes were shot with different camera.
AI and machine learning software on iPad OS15 (and iOS 15) now has a virtual colorist actively adjusting your shots and enhancing and color matching them while you sleep. That is basically insane. That’s probably why it appeared that the photos and even the iPad itself had been upgraded.
Ok, I could go on and on about that one feature, but let’s move to some more features. There are also new effects that are added that vary with each memory (there are a lot more clips being generated, including various versions of the same idea to choose from).
In the experiments so far the effects are clearly better and more subtle than in iOS 14. Again in many cases I found myself saying the word “beautiful” when I tried find an adjective to describe the results.
For shots that have a vertical bias there’s a vertical geometric split screen effect, often with a thin black border, and it has a kind of 60’s on steroids feel with the bars sliding in and out and resizing into place.
Another effect not seen in iOS 14 is a kind of circular rotation – great for landscapes – it’s not a common effect probably because it is computationally complex, but for the AI, it’s a snap. Sometimes this effect has a kind of blur-dissolve added which makes it fun and, again, still tasteful.
It appears that the effects are not only better and there’s a larger bag of them, but they appear to evolve and adapt to the content, that is to say that the speed and depth of each changes with the music combined with the photo and video content.
Oh, and the music. OMG. Each clip has 6 songs pre-selected and the entire clip adapts, in real time (!), when you change the song, showing you various styles and looks that match. Apparently Apple Music is also connected if you have a subscription.
As a mater of fact, it is hard to be certain, as we have not had more than a few hours to test this, but nearly everything appears to be “live” and constantly evolving in real time. In order to “freeze” a version of a memory you have to “favorite” it (with the typical heart symbol) and then “add to memories” in order to edit (change the names or choose more images – or remove anything if it is not to your liking).
There is so much more not yet mentioned here: this article could probably be a book
The AI is also getting creative with names and “concepts” for the clips. For example, if you had lunch (or took photos) over the years in the same city (for me it was Knoxville, TN) it might look at the coincidence that you tended to take photos around midday in that town and then create a memory clip called “Lunch in Knoxville over the Years”. Or for example the clip at the head of this article: “Golden Hour Over The Years”.
This is an early and primitive foretaste of the literary ambitions of AI. In the new Photos App in iOS 15 it is beginning to “think” about when, where and why humans take photos and videos and then conceiving a story that fits the behavior it is witnessing.
Other titles go beyond the basic “Amsterdam in 2016” and start to use the understanding and visual ability to “see” what is in the photo to create a clip like : “Playing in the Snow at Christmas”. Snow? Does it know it’s cold? Maybe just that it’s white and happens in the northern hemisphere in December. This is just the very beginning of something that will evolve, hourly, from now on. I can’t wait.
Above: Photo Collage / Lynxotic / Johns Hopkins University Press
There’s a massive migration coming as the physical and political landscape changes
A gradual, subtle, yet immensely important shift is underway across the planet. That shift is the change in thinking that will be required to accompany the changes that we now know, for a fact, are coming. Global warming, sea level rise, mass decentralization and migration and many more macro trends that are no longer in doubt but will be a reality to cope with.
Taking the positive approach to this – searching for solutions to the many huge geopolitical and technological issues that we face, is a trend that must come to the front and center of our dialog about the future.
Although, it is a book more thought of as a guide for city planners and other professionals, Unlocking the Potential of Post-Industrial Cities is fascinating evidence of where these forced changes could lead, and what potentials can be unlocked by the opportunities that will inevitably arise from the extreme, changing circumstances.
A great step in the right direction, we’ve provided a look at Unlocking the Potential of Post-Industrial Cities, by Matthew E. Kahn and Mac McComas, below, along with a description, provided courtesy of the Bookshop (and the publisher), along with some links for a variety of options where to purchase.
The urban centers of New York City, Seattle, and San Francisco have enjoyed tremendous economic success and population growth in recent years. At the same time, cities like Baltimore and Detroit have experienced population loss and economic decline. People living in these cities are not enjoying the American Dream of upward mobility.
How can post-industrial cities struggling with crime, pollution, poverty, and economic decline make a comeback? In Unlocking the Potential of Post-Industrial Cities, Matthew E. Kahn and Mac McComas explore why some people and places thrive during a time of growing economic inequality and polarization–and some don’t.
They examine six underperforming cities–Baltimore, Cleveland, Detroit, Philadelphia, Pittsburgh, and St. Louis–that have struggled from 1970 to present. Drawing from the field of urban economics, Kahn and McComas ask how the public and private sectors can craft policies and make investments that create safe, green cities where young people reach their full potential. The authors analyze long-run economic and demographic trends.
They also highlight recent lessons from urban economics in labor market demand and supply, neighborhood quality of life, and local governance while scrutinizing strategies to lift people out of poverty. These cities are all at a fork in the road.
Depending on choices made today, they could enjoy a significant comeback–but only if local leaders are open to experimentation and innovation while being honest about failure and constructive evaluation.
Unlocking the Potential of Post-Industrial Cities provides a roadmap for how urban policy makers, community members, and practitioners in the public and private sector can work together with researchers to discover how all cities can solve the most pressing modern urban challenges.
Having two plans to save the world, and being Elon Musk, the questions are fascinating and a bit bizarre
It was bound to happen, sooner or later. So many fantastic triumphs over evil – starting a company with a goal of accelerating sustainable energy and transportation. And then , not only succeeding at that but challenging the fossil fuel industrial complex, beating them, then basically forcing the major automakers across the globe to finally make the shift into all electric vehicles.
And SpaceX, though launching rockets is a messy thing, at least the Starlink Satellite Broadband internet project is something that will help humans all over the earth to decentralize, potentially a much needed option, if or when the coastlines begin to shrink and overpopulated coastal megalopolises are at the bottom of the ocean.
Forever win streak has an end in sight?
But Mars? There are some questions about that. For example, if the Earth rescue is so important, and if it succeeds (please!) then why would anyone want to live in a place like Mars?
Elon Musk replies cryptically to this lovely Mars Clip
As Shannon Stirone wrote in the Atlantic this week: Mars Is a Hellhole. And further: Colonizing the red planet is a ridiculous way to help humanity. Ok. There are issues. It’s a bit cold, an average surface temperature is a deadly 80 degrees below zero according to the article. Wow, and it has no magnetic field to help protect its surface from radiation from the sun or galactic cosmic rays; it has no breathable air.
Those are all enough for anyone to want to double down on the whole “let’s fix the earth” thing.
Unless…. Musk being the genius that he is, could it be that he is hedging his bets? Has he basically already decided that this whole Climate Change thing has already gone too far? And Earth is beyond saving?
Others have pointed out that by putting even a tiny fraction less effort into saving this planet in order to try and colonize another one, one that is 3.7 billion miles away, btw, could jeopardize the slim chance still there that climate change can be slowed, stopped, even reversed before it’s too late.
A list of goals and accomplishments that dovetail nicely into a world saved, or?
So what is the Mars thing really about then? I have to be honest it might be just fine. Give “Emperor Elan” the benefit of the doubt. Tesla’s are damn S3XY and they are also a perfect first step into transforming the world transportation and even energy generation and storage into something sustainable, and that’s downright perfect: utopia and having the time of your life all at once.
So, why not just throw in Mars and a nice little colony there, just for kicks? The whole mental-telepathy, Neurallink, thing, that’s gotta be useful too and, along with AI and Hyper-loop, let’s do it all, shall we?
Perhaps it does all fit together in some way that is invisible to the rest of us. Why, when Earth seems to need all our attention, particularly with political inaction and even obfuscation and attempted sabotage of the paths to a green future, why put so much into Mars right now?
Hopefully the answer is right around the corner, or at least less than 3.7 billion miles away.
If four years of the Former Guy taught us anything, it’s that we have no time left for evil, soulless greed run amok
– Opinion & Analysis –
Recent attempts by politicians, beholden to the fossil fuel industry in Texas, to use the collapse of the energy infrastructure during the recent weather disaster as an opportunity to bash and trash wind and solar energy is an example of an unfortunate, banal and still common form of pure evil.
The deeper connections, easily seen lurking just beneath the surface, are rich and multilayered.
If this extreme weather disaster is one of many that are linked to climate change, a manifestation of dangers that climate scientists have been warning of for decades, the irony goes beyond just sick.
Wind and solar energy exist as an early and tentative positive step toward somehow stopping, or at least slowing down, the negative man-made climate change repercussions before it is too late.
The real reasons behind the Texas power grid collapse are related to traditional fossil fuel based energy sources and bad management of the energy infrastructure that can be traced back to an arrogant belief that Texas is better off without connections to the national system.
The local political response to this eminently preventable catastrophe was to bash and trash and blame the very technology that, ultimately, is part of a tentative start to actually begin to solve the bigger problem of man-made climate change.
…the time is gone to accept “two sides” to an argument that, by postponing any real solutions, will kill us all.
Just as the history of the internal combustion engine and the fossil fuel and auto industry’s attempts to prolong its near monopoly, using disinformation and other tactics for over 50 years was evil, the anti-sustainable energy politics in Texas today is just a continuation of that effort.
The time is gone to accept “two sides” to an argument that has one side trying, by attempting to postpone any real solutions, to kill us all, in the name of short term greed.
Under unique circumstances lending legitimacy to evil is too costly to condone
Looking at “both sides” of an issue is a practice based on a theory that “reasonable people” can disagree on diametrically opposed views. This idea is often suspended, however, by unreasonable people for their own reasons. That is sometimes called “war”.
Reasonable people, people, for example that understand climate science and want to prevent the total destruction of the earth and the extinction of all inhabitants, are often reluctant to suspend this idea of “good people on both sides” by their very nature as caring individuals.
“Now we need to understand that the “silence of one good man” can spell disaster for all good people. Each of us who remained passive as our impending disaster continued might have been the one “good man” who didn’t act, didn’t speak out, didn’t resist…
Now is a time when huge changes are going to be forced by an external and highly powerful and dangerous threats to our survival. The changes that are needed involve radically new ways of thinking and acting across many spheres of activity.
Subscribe to our newsletter for all the latest updates directly to your inBox.
New technologies, such as the aforementioned wind turbines and solar collectors, new forms of transportation, new ways of looking at other causes of, and remedies to, the excessive expulsion of carbon into the atmosphere will be absolutely required.
The truth is that for these new ways of thinking and acting to take over in human commerce the old ways must be cancelled. With extreme prejudice.
The past and those that want to go back to it are a lost cause, unfortunately
Many many “rich” people will be unhappy about this. And they will have politicians in their pocket that will gladly spread lies and disinformation to try and sustain the sick, evil gravy-train of polluting, carbon spewing systems as long as possible.
Sick and evil, not because those ways of surviving for humanity, burning fossil fuels and using them for a million different things that were a benefit in the short term, but because the short term is over.
The various arguments that somehow it is a good idea not to change and for the changes to slow down and not step on any toes as they gradually become “viable” have zero validity as of today (really as of 25 years ago but that’s water under the bridge).
Eventually the climate itself will kill them for their mistakes. Unfortunately it will also kill the rest of us if we allow them to continue to postpone positive change with lies and disinformation.
– D.L.
There must be an understanding among “reasonable” people, people who want to be part of an urgent crusade to save the world, literally, that points of view and the people who espouse them represent evil, plain and simple.
They will scream that reasonable people are “femi-nazis and “eco-terrorists” and say and do whatever it takes to protect what’s left of a deadly status quo. But they are wrong.
Eventually the climate itself will kill them for their mistakes. Unfortunately it will also kill the rest of us if we allow them to continue to postpone positive change with lies and disinformation.
“Every one of these people is the banality of evil personified. Every one of them became what Arendt called a “leaf blowing in the whirlwind of time.” Now every one of them bears responsibility for what could lie ahead.”
This change in thinking about how to respond to this kind of evil will be a more important factor in the survival of humanity than all the technological advances combined.
“World War III is a guerrilla information war with no division between military and civilian participation.” – Marshall McLuhan (1970), Culture is Our Business, p. 66.
–Marshall McLuhan
“Info-wars” were predicted as the battlefield of WWIII by Marshall McLuhan in 1970 and now we are in it and there must be an understanding of what is at stake.
When disinformation is used as a perennial weapon against positive, necessary change it is necessary to do more than disagree. It is necessary to expose the lies and, more importantly, the obvious sick and criminal motives for the lies. Over and over as often as necessary.
Adobe has added some significant updates to Photoshop in the last 6 months. As a daily user in a digital publishing environment, we have been able to test and use many of the new features in a real-world setting.
By way of some general background. I was a user of the CS4 bundle up until 2013 when the Creative Cloud system first launched. At first the idea of paying a monthly subscription fee rather than upgrading only when “absolutely necessary” was not immediately a comforting proposition.
However, over time the improvements, along with the huge list of including software, in addition to Photoshop, won me over.
Adobe does face steep competition from Affinity Photo, which continues to have the “buy once-use-forever” model and also has free updates quite often.
We also use Affinity Photo and it is in many ways more user friendly than Photoshop – particularly if you are not already deep into the Adobe software UX.
At the same time, it appears that the competition has only done what competition is supposed to do: made both products better.
The world changed when the 99% of the labor disappeared from replacing photo backgrounds
That same competitive marketplace may even be the reason that, during the last year, Adobe’s upgrades have accelerated and become more than just ho-hum superficial changes: they are now mind-blowing, and that on a regular basis.
In our shop, it really started to get interesting with the upgrade to the “quick selection tool” in June 2020. A new button was added: “select subject” removed the need to painstakingly manually select a subject (such as a person or object) and the new “select and mask” option opens a fine adjustment window to fine tune the mask.
Very often no further adjustments are needed to separate a subject from the background and then begin background layering and various other typical uses for these features. Once again, the time of this upgrade seemed to coincide with competition: a web based platform (that also built a photoshop plug-in) called Remove BG gained some popularity in late 2019, apparently prompting Adobe to fight back.
“Beginning with Photoshop 21.2 (June 2020 release), Select Subject is now content-aware and applies new custom algorithms when it detects a person is in the image. When creating a selection on portrait images, treatment around hair area has been vastly improved to create a detailed selection of hair.”
— Adobe Support
And fight back they did. The new automated “select subject” system was pretty usable at first release. But the upgrades since then have been nothing less than astounding. Sometimes it seems like the performance of this new system gets better daily, as if stealth over-the-air upgrades are happening outside of the official ones. Probably not but the bottom line is this really reduces the time and effort to nearly zero.
Naturally, for complex or difficult photos, or for situations where an absolutely perfect high resolution separation (of, say, a very fluffy haired top model for a huge ad campaign etc.) the old, time consuming and labor intensive techniques would be required.
But for everyday digital news style creative collage applications and any situation where it just have to look realistic (or create a fantasy tableau) it is lightening fast and very very usable.
Neural and AI based updates have begun and will accelerate big-time in 2021
In October, 2020 Adobe introduced 8 new neural filters to the platform. In the video above you can see the general state of the filters around the time of the release. Without getting into granular detail in text, you can see the highlights and the carious methods of use in the video.
What I want to emphasize beyond the existence and fascinating implications for these new tools is the fact that they represent just a tiny hint at the potential for these and many more totally new functions and applications that are going to explode on the scene in 2021.
These kinds of new capabilities for photo manipulation software are likely to take years to be absorbed in to the workflow and toolkit of the millions of users across the globe. And, even as we “struggle” to learn how to benefit from the lack of expertise needed to achieve results heretofore either impossible or only realized with many hours of painstaking profession work, new even more mind-blowing upgrades are coming.
Some examples can be seen in the video below. Additionally there will be a new version of Photoshop available in 2021 to take advantage of the Apple Mac M1 chips and mac OS11 Big Sur.
These will accelerate even more the image manipulation and automated creation options within Photoshop and creative cloud. Honestly, it is now the user, with minimal effort, who will be using imagination and creativity, nearly in isolation, to create previous unimaginable images. Think = do. That’s where this is headed.
“The Social Dilemma” a documentary now available to watch on Netflix, exposes some hard truths and dangers of social networking. Former employees from juggernaut tech companies including Facebook, Twitter, Instagram, Pinterest and many others are interviewed, many of whom co-invented and developed the very structures and business models that are creating major problems as broken-down and discussed in the docu-drama.
Not much of a spoiler alert, but social media companies not only sell our user data, but in conjunction use all that data to create an ultra-sophisticated psychological profile, ultimately to have the powerful ability to manipulate us. Your privacy, surveillance capitalism, positive intermittent reinforcement, artificial intelligence (AI), algorithms, dopamine hits, are just some of the terms used within the film and very much prevalent in social media.
There are only two industries that call their customers ‘users’: illegal drugs and software”
Edward Tufte
We’ve curated a list of books written by the former tech employees that appeared in the documentary, as well as provided some additional information from the publisher. Click to see more book information, we’ve provided links for purchase that if interested that helps out independent books stores.
We live in the age of the algorithm. Increasingly, the decisions that affect our lives–where we go to school, whether we can get a job or a loan, how much we pay for health insurance–are being made not by humans, but by machines. In theory, this should lead to greater fairness: Everyone is judged according to the same rules.
But as mathematician and data scientist Cathy O’Neil reveals, the mathematical models being used today are unregulated and uncontestable, even when they’re wrong. Most troubling, they reinforce discrimination–propping up the lucky, punishing the downtrodden, and undermining our democracy in the process. Welcome to the dark side of Big Data.
NEW YORK TIMES BESTSELLER – A former Wall Street quant sounds the alarm on Big Data and the mathematical models that threaten to rip apart our social fabric–with a new afterword. “A manual for the twenty-first-century citizen . . . relevant and urgent.”–Financial Times. NATIONAL BOOK AWARD LONGLIST – NAMED ONE OF THE BEST BOOKS OF THE YEAR BY The New York Times Book Review – Boston Globe – Wired – Fortune – Kirkus Reviews – The Guardian – Nature – On Point
Automating Humanity is an insider’s perspective on everything Big Tech doesn’t want the public to know–or think about–from the addictions installed on a global scale to the profits being driven by fake news and disinformation, to the way they’re manipulating the world for profit and using our data to train systems that will automate jobs at an explosive, unprecedented scale.
Toscano provides a critique of modern regulation, including parts of the new European Union’s General Data Proctection Regulation (GDPR) suggesting how we can create proactive, adaptable regulation that satisfies both the needs of consumer safety and commercial success in the international economy. The content touches on everything from technology, economics, and public policy to psychology, history, and ethics, and is written in a way that is accessible to everyone from the average reader to the technical expert. Click Here to See “Automating Humanity” and help Independent Bookstores. Also Available on Amazon.
The Age of Surveillance Capitalism by Shoshana Zuboff
In this masterwork of original thinking and research, Shoshana Zuboff provides startling insights into the phenomenon that she has named surveillance capitalism. The stakes could not be higher: a global architecture of behavior modification threatens human nature in the twenty-first century just as industrial capitalism disfigured the natural world in the twentieth.
Zuboff vividly brings to life the consequences as surveillance capitalism advances from Silicon Valley into every economic sector. Vast wealth and power are accumulated in ominous new “behavioral futures markets,” where predictions about our behavior are bought and sold, and the production of goods and services is subordinated to a new “means of behavioral modification.”
The threat has shifted from a totalitarian Big Brother state to a ubiquitous digital architecture: a “Big Other” operating in the interests of surveillance capital. Here is the crucible of an unprecedented form of power marked by extreme concentrations of knowledge and free from democratic oversight. Zuboff’s comprehensive and moving analysis lays bare the threats to twenty-first century society: a controlled “hive” of total connection that seduces with promises of total certainty for maximum profit–at the expense of democracy, freedom, and our human future. Click Here to See “The Age of Surveillance Capitalism” and help Independent Bookstores. Also Available on Amazon.
Ten Arguments for Deleting Your Social Media Accounts Right Now by Jaron Lanier
You might have trouble imagining life without your social media accounts, but virtual reality pioneer Jaron Lanier insists that we’re better off without them. In Ten Arguments for Deleting Your Social Media Accounts Right Now, Lanier, who participates in no social media, offers powerful and personal reasons for all of us to leave these dangerous online platforms.
Lanier’s reasons for freeing ourselves from social media’s poisonous grip include its tendency to bring out the worst in us, to make politics terrifying, to trick us with illusions of popularity and success, to twist our relationship with the truth, to disconnect us from other people even as we are more “connected” than ever, to rob us of our free will with relentless targeted ads. How can we remain autonomous in a world where we are under continual surveillance and are constantly being prodded by algorithms run by some of the richest corporations in history that have no way of making money other than being paid to manipulate our behavior? How could the benefits of social media possibly outweigh the catastrophic losses to our personal dignity, happiness, and freedom? Lanier remains a tech optimist, so while demonstrating the evil that rules social media business models today, he also envisions a humanistic setting for social networking that can direct us toward a richer and fuller way of living and connecting with our world. Click Here to See “Ten Argument for Deleting Your Social Media Accounts” and help Independent Bookstores. Also Available on Amazon.
The Righteous Mind by Jonathan Haidt
Click Here to See “The Righteous Mind“ and help Independent Bookstores. Also Available on Amazon.
Drawing on his twenty five years of groundbreaking research on moral psychology, Haidt shows how moral judgments arise not from reason but from gut feelings. He shows why liberals, conservatives, and libertarians have such different intuitions about right and wrong, and he shows why each side is actually right about many of its central concerns. In this subtle yet accessible book, Haidt gives you the key to understanding the miracle of human cooperation, as well as the curse of our eternal divisions and conflicts. If you’re ready to trade in anger for understanding, read The Righteous Mind.
In this “landmark contribution to humanity’s understanding of itself” (The New York Times Book Review) social psychologist Jonathan Haidt challenges conventional thinking about morality, politics, and religion in a way that speaks to conservatives and liberals alike. Click Here to See “The Righteous Mind” and help Independent Bookstores. Also Available on Amazon.
First is was the FaceApp that added years to your face with its app filter, in the FaceApp Challenge – with questionable issues regarding the origins (Russia) and terms of service agreement.
Now, from a more reassuring source, namely researchers in the US, including some from the MIT-IBM Watson AI Lab, we have the opportunity to see our selfies (and celebrity snaps) transformed into pseudo-classical portrait styles.
The web site upload system, currently down due to massive demand, uses GAN (Generative Adversarial Network) results from 45,000 images in the art history archives to create a new photo based on the original plus the relevant data instructions from the scan.
“With AI Portraits Ars anyone is able to use GAN models to generate a new painting, where facial lines are completely redesigned.
The model decides for itself which style to use for the portrait. Details of the face and background contribute to direct the model towards a style.
In style transfer, there is usually a strong alteration of colors, but the features of the photo remain unchanged. AI Portraits Ars creates new forms, beyond altering the style of an existing photo.”
AI Portraits Ars Web Site
As can be seen from the montage above (and the version with names added below) the results are often flattering in an odd ancient sort of way. Also, some, such a Keanu Reeves, are obvious (?) whereas others you might never guess!
So below the results and thanks for playing!
The AI Portraits web site should be back up shortly, assuming the rush to try it out eventually slows!
On the one hand, after more than a decade of growth and pure digital news models showing potential financial viablility, profitability remains elusive. On the other, a tsunami of artificial intelligence, software and hardware improvements over the last 2 years, in particular, have begun to reduce overheads, especially for those bulk production techniques such as employed by BuzzFeed.
While legacy publishers are showing some marginal improvement in subscription revenues, the business model for online media and content production continues to shift in search of a sustainable income mix. Cost of human contributions to content is an obvious issue.
“The restructuring we are undertaking will reduce our costs and improve our operating model so we can thrive and control our own destiny, without ever needing to raise funding again”
.@peretti email to staff: “Revenue growth by itself isn’t enough to be successful in the long run. The restructuring we are undertaking will reduce our costs and improve our operating model so we can thrive and control our own destiny, without ever needing to raise funding again” https://t.co/vvpCnMhPNF
Lowering overhead by cutting staff is the message sent as the primary explanation for the industry-wide layoffs. Digging just beneath the surface, however, is the not-so-gradual shift in technology that allow digital content production organizations to ramp up output while at the same time reducing costs.
Read: more work done by A.I., software and robots and fewer humans required. Result: Accelerated Digital Deflation.
The entire history of tech advances since the ubiquity of the personal computer has engendered digital deflation (ask anyone in the music industry). Meanwhile, advancements over the last couple of years are creating a massive acceleration of this trend, based on a shift toward automated production in all facets of content creation.
As a content creator the perspective seems amusingly bifurcated; improved tools for visual and verbal expression must be welcomed and adapted to, all while working in a monetization system that does not yet favor the individual creator.
Perhaps a headline: “Thousands of Humans Rendered Obsolete By Improved Robot Software” would seem less compassionate than merely indicating that they (the humans) stood in the way of reaching profitability?
In the long run, using more A.I., together with improved hardware and software tools to increase productivity in digital communication, will lead to lowered barriers to entry. And, for content creators and those 1000+ professionals just liberated, it might be best to consider all their options. One of the best may be to establish a free-lance future using the very technology that erased those jobs in the first place.
![iPadOS 15 Preview: [Part 2] Deep Dive - AI and Machine Learning that will Blow You Away](https://i.ytimg.com/vi/XrU6cNxC1rM/hqdefault.jpg)
