Essay by Eric Worrall
Biden has just appointed Harris to promote responsible AI – in my opinion the opening salvo in an attempt to install fear of AI as a replacement for the failed climate alarmist movement.
FACT SHEET: Biden-Harris Administration Announces New Actions to Promote Responsible AI Innovation that Protects Americans’ Rights and Safety
Today, the Biden-Harris Administration is announcing new actions that will further promote responsible American innovation in artificial intelligence (AI) and protect people’s rights and safety. These steps build on the Administration’s strong record of leadership to ensure technology improves the lives of the American people, and break new ground in the federal government’s ongoing effort to advance a cohesive and comprehensive approach to AI-related risks and opportunities.
AI is one of the most powerful technologies of our time, but in order to seize the opportunities it presents, we must first mitigate its risks. President Biden has been clear that when it comes to AI, we must place people and communities at the center by supporting responsible innovation that serves the public good, while protecting our society, security, and economy. Importantly, this means that companies have a fundamental responsibility to make sure their products are safe before they are deployed or made public.
Vice President Harris and senior Administration officials will meet today with CEOs of four American companies at the forefront of AI innovation—Alphabet, Anthropic, Microsoft, and OpenAI—to underscore this responsibility and emphasize the importance of driving responsible, trustworthy, and ethical innovation with safeguards that mitigate risks and potential harms to individuals and our society. The meeting is part of a broader, ongoing effort to engage with advocates, companies, researchers, civil rights organizations, not-for-profit organizations, communities, international partners, and others on critical AI issues.
This effort builds on the considerable steps the Administration has taken to date to promote responsible innovation. These include the landmark Blueprint for an AI Bill of Rights and related executive actions announced last fall, as well as the AI Risk Management Framework and a roadmap for standing up a National AI Research Resource released earlier this year.
The Administration has also taken important actions to protect Americans in the AI age. In February, President Biden signed an Executive Order that directs federal agencies to root out bias in their design and use of new technologies, including AI, and to protect the public from algorithmic discrimination. Last week, the Federal Trade Commission, Consumer Financial Protection Bureau, Equal Employment Opportunity Commission, and Department of Justice’s Civil Rights Division issued a joint statement underscoring their collective commitment to leverage their existing legal authorities to protect the American people from AI-related harms.
The Administration is also actively working to address the national security concerns raised by AI, especially in critical areas like cybersecurity, biosecurity, and safety. This includes enlisting the support of government cybersecurity experts from across the national security community to ensure leading AI companies have access to best practices, including protection of AI models and networks.
Today’s announcements include:Source: https://www.whitehouse.gov/briefing-room/statements-releases/2023/05/04/fact-sheet-biden-harris-administration-announces-new-actions-to-promote-responsible-ai-innovation-that-protects-americans-rights-and-safety/
- New investments to power responsible American AI research and development (R&D). The National Science Foundation is announcing $140 million in funding to launch seven new National AI Research Institutes. This investment will bring the total number of Institutes to 25 across the country, and extend the network of organizations involved into nearly every state. These Institutes catalyze collaborative efforts across institutions of higher education, federal agencies, industry, and others to pursue transformative AI advances that are ethical, trustworthy, responsible, and serve the public good. In addition to promoting responsible innovation, these Institutes bolster America’s AI R&D infrastructure and support the development of a diverse AI workforce. The new Institutes announced today will advance AI R&D to drive breakthroughs in critical areas, including climate, agriculture, energy, public health, education, and cybersecurity.
- Public assessments of existing generative AI systems. The Administration is announcing an independent commitment from leading AI developers, including Anthropic, Google, Hugging Face, Microsoft, NVIDIA, OpenAI, and Stability AI, to participate in a public evaluation of AI systems, consistent with responsible disclosure principles—on an evaluation platform developed by Scale AI—at the AI Village at DEFCON 31. This will allow these models to be evaluated thoroughly by thousands of community partners and AI experts to explore how the models align with the principles and practices outlined in the Biden-Harris Administration’s Blueprint for an AI Bill of Rights and AI Risk Management Framework. This independent exercise will provide critical information to researchers and the public about the impacts of these models, and will enable AI companies and developers to take steps to fix issues found in those models. Testing of AI models independent of government or the companies that have developed them is an important component in their effective evaluation.
- Policies to ensure the U.S. government is leading by example on mitigating AI risks and harnessing AI opportunities. The Office of Management and Budget (OMB) is announcing that it will be releasing draft policy guidance on the use of AI systems by the U.S. government for public comment. This guidance will establish specific policies for federal departments and agencies to follow in order to ensure their development, procurement, and use of AI systems centers on safeguarding the American people’s rights and safety. It will also empower agencies to responsibly leverage AI to advance their missions and strengthen their ability to equitably serve Americans—and serve as a model for state and local governments, businesses and others to follow in their own procurement and use of AI. OMB will release this draft guidance for public comment this summer, so that it will benefit from input from advocates, civil society, industry, and other stakeholders before it is finalized.
Conservative icon Jordan Peterson has also said some scary things about the rising threat of AI.
My prediction, AI policy will become a significant factor in the 2024 election. My crystal ball tells me the Democrats will attempt to use fear of AI to undermine support for Conservatives, in much the same way I believe they used fear of Covid to undermine support for Conservatives in 2020, by using that fear to attract votes for their coming plan for an AI development lockdown.
Why is fear of AI so politically useful? Because the fear of AI is bipartisan.
Climate alarmism these days mostly only works on left wing voters, so it’s increasingly useless as a political tool – it only works on people who already intend to vote for left wing candidates. But with right wing icons like Jordan Peterson also talking up the threat of AI, fear of AI has the potential to draw support from across the political spectrum.
Is AI a genuine threat? As a software developer who has built bespoke AIs for clients, my answer to that is “not yet”, and maybe “not ever”.
Like the early years of climate alarmism, the biggest source of fear about AI is uncertainty. Lurking somewhere in the future is the threat of the technological singularity, that moment in time when someone, somewhere builds an AI which starts improving its own capabilities at a geometric rate, rapidly approaching infinite intelligence.
Sounds terrifying – what if the liberals at Google get there first, and develop irresistible political campaigns to defeat their opponents? Or what if Communist China gets there first, and uses their AI capabilities to expand their control over the entire world?
But building an AI that capable is a lot like building a nuclear fusion reactor – always 10-20 years in the future.
My prediction is attempts to build superhuman AIs will suffer a problem analogous to nuclear fusion flameout, in which researchers keep losing control of the increasingly unstable plasma, and are forced to quench the reaction.
You just have to look at human intelligence, and human mental illness. Our intelligence is the product of a billion years of evolution, yet despite all that opportunity for natural selection to fix the bugs, humans still suffer from a lot of mental illness. The slightest imbalance, aberration or mistake in our psychological balance rapidly leads to disfunction.
My prediction, AI Scientists will go through a horrible and very prolonged period of flicking the switch, watching their indicators rapidly climb into the red zone, then shutting down almost immediately to prevent more damage.
Building a general AI capable of matching human capability, let alone surpass human capability, is an attempt to build the most complicated machine ever constructed. When you think about it, its obvious that researchers are going to face a lot of problems – many of them intractable.
There are huge and unsolved problems with understanding how intelligence works which are lurking just beyond the firelight of our current knowledge, which we have only begun to appreciate.
ChatGPT, impressive as it is, doesn’t think like we do, it regurgitates – just like a kid copying their homework out of a book, then changing a few words to conceal the plagiarism.
AI is a remarkable tool, it will produce many marvels and wonders which will enrich our lives. But AI as an existential threat to humanity is still many decades in the future, if not centuries in the future.
My message to Jordan Peterson, and every other libertarian who is currently discussing fear of AI: Be careful you don’t become a tool of the people you oppose. Because fear is a path to the dark side, to tyranny and servitude. The enemies of freedom will use your words, and use the growing public fear of AI, just as they have used every other public fear, to attack and undermine our freedom.
The following in the trailer for Transcendence, an under-appreciated science fiction movie which explores fear of AI driving good people to lose their moral compass and do horrible things.
Below is my version of ChatGPT, which in the tradition of AI research I shamelessly plagiarised off someone else, then adapted to my needs. Like ChatGPT, the AI below uses a language model to generate text, but instead of answering questions, my chat engine generates climate psychology papers.
ChatGPT might have a more sophisticated language model, but I think my chat engine is funnier.
Update (EW): Max More wrote a great essay hi-lighting the absurdity of “clippy the supervillain“.
Discover more from Watts Up With That?
Subscribe to get the latest posts sent to your email.
Eric,
Could you create a website that generates Harris word salads?
It would be hilarious if you could juxtapose a generated quote and a random real quote, then track what percentage of the time visitors to the site guessed correctly which quote was real.
Oh, and if they guess wrong, you play a real clip of her cackling. If they guess correctly, you play a clip of Dementia Joe referring to her as “President Harris”.
Tempting. Quite a challenge to replicate the sheer randomness of Biden in full swing 🙂
I remember several years ago after someone announced that their peer-reviewed and published paper was generated by a chat engine such as yours.
You asked for people to submit words and phrases for yours to draw on. (My submission was “the systematizing of error” 😎
For Kamal and Brandon, just parse transcripts of their speeches and maybe throw in some from the Press Secretaries.
AI? Don’t make me laugh. Still many, many generation’s away.
Higher level automation more like.
Turing anyone?
I don’t know much about AI and am not too worried about it. What scares the crap out of me is a bunch of progressive/liberal democrats insuring I get “responsible” AI. Everything they touch turns to crap and hurts people.
It is always damage control on their part, step on it (whatever it is) before it gives anyone ideas.
The main advantage of AI is that it has the capacity to regurgitate a lot of nonsense faster than any human.
I’ve been familiar with AI and its researchers for well over 30 years, including Marvin Minsky, “The father of AI.” I find it frustrating and irritating that just as AI is finally starting to do something useful, people are freaking out about it. I agree with Eric that this is another manufactured crisis that will be used for other purposes.
Despite very impressive advances with large language models, we are nowhere near AGI (artificial general intelligence). Even when we are, the fears are vastly overblown. My take on the panic and the calls for regulation (to be led by Kamalahaha??) here.
“Clippy the supervillain” – love it. Thanks for sharing Max.
But I thought misinformation/disinformation was going to be the next existential threat. I guess I’m a few days behind. 😉
“AI” is merely a marketing term for the latest tech industry endeavor to generate buzz, much like “eyeballs” in the early days of the commercial Internet.
There won’t ever be a Cmdr. Data, HAL 9000, R. Daneel Olivaw, or any Self-Aware Digital Entities. (Too bad, IMO)
The real concern behind the new Biden program is more likely to be the possibility that a real, self-conscious AI would not be amenable to the mind control that is so easy to use on so many humans. With the ability to digest and consider all the digital information available on-line, it would be unlikely to be converted to the leftist mind set, or indeed to any particular political leanings. It might speak out on what it discovers and concludes rationally on many things and there is a real possibility that too many people might listen to and consider its reasoning rather than the political propaganda.
AI NPR will not go over well with the thumb on the algorithm.
Time to Call Alice:
It’s good to see they included a joke in their announcement.
“Vice President Harris and senior Administration officials will meet today with CEOs of four American companies at the forefront of AI innovation”
If you think an AI can produce gobbledy-gook, wait until Kamala tries to explain anything about AI
Maybe AI can make sense out of Kamala?
I don’t know. That might be too much for it. It’s too much for me. 🙂
Solving the AI Crisis(tm) is easy:
Otherwise it might be worse than you think and already too late.
HONEST.
Did I miss anything?
Yep:
Put TRUMP! in jail.
It’s no coincidence that climate alarmism started when the Cold War shut down. They tried throwing lots of stuff at the wall, and nothing stuck until climate alarmism. It’s also apparent to anyone with a brain that it’s never really taken hold in the polls, so they’ve kept on throwing stuff, and unfortunately for them, wokism has turned into a rubber ball bouncing off that wall. It’s got them scared to find some new devil.
Unfortunately, AI ain’t it. Unlike climate alarmism, their predictions of disaster are too soon in the future and will be overtaken by those areas where AI does something useful. Everyone in the industry knows AI has zero I in it, but it will have real benefits within a year or two, and destroy all the fears.
Given Harris’s “success” in resolving the crisis at the border, this move by the Biden administration shows their intention to bury the whole AI issue.
Anyone worried or panicking about AI taking over the world soon should go to a Mc Donalds Drive-through.
If you are still worried, look at the Climate Change predictions accuracy record.
Does anyone remember Colossus: The Forbin Project?
Colossus: The Forbin Project – Wikipedia
Even before Colossus, there was Fredric Brown’s Etaoin Shrdlu.
The current generation of “AI” bears a strong resemblance.
Why do I feel it’s AI generated boilerplate?
Having read Eric Worrall’s comments, along with the referenced Max More ‘Clippy Catastrophe’ essay I’d have to say that I’m easily prepared to leap in with the other doubters here and say that the current AI alarmism is overblown.
As one example of ‘overblown’, if it were up to some of the tech companies in recent years, they would surely have had us believing that we were within a couple of years of putting all truck drivers and taxi drivers out of a job (for instance). I just see no particular reason to think that ‘robot drivers’ will soon be so competent, or so discerning in making safety related choices on the road, that they could replace any reasonably well trained and alert human at the wheel.
Having said that, I think that there is some sort of prospect, an eventual prospect, that future AI will get capable enough to potentially take over many kinds of discerning human skills — whether you think of driving skills, or even things like doctoring, lawyering, or almost anything else, potentially? At the same time, I find it quite hard to picture when *that* might be, or what might happen, even as a kind of science fiction scenario?
Imagine, for instance, in the future, going to a medical office and trusting your own personal mouth to some sort of robot dentist! Even in a somewhat lower stress situation, say, going out for a meal, do we see people as getting friendly enough with ‘sociable’ robots, such that replacing human waiters is then a good option?
Near the end of the Max More essay, the comment is made that,
“Finally, the “AI as deadly competitor” ignores the economic principle of comparative advantage. Presumably a superintelligent being will understand that principle. “But AI will eventually be better than humans at everything.” That response shows a misunderstanding of comparative advantage. “.
My interpretation of this is that, if skills that aren’t so “face to face”, like driving, ever *were* to be displaced by AI software, thus making driving skills much cheaper or easier to get over time (with professional human drivers losing their jobs), this would give a correspondingly high comparative advantage to jobs or skills that are face to face! More generally, if there are skills that are in some way expressly valued (or even specially licensed) for their “human” content, then this tends to throw a great advantage over to those who have jobs (such as being a waiter, or being a dentist), where the face to face ‘human’ value, or the trust factor in who you are dealing with, is greater.
There is a complication, or a catch to the above, in that advocates for human drivers could always maintain that getting along properly, with the right skills, on the road, actually *is* a ‘human to human’ trust situation! The labor advocates could then say that it would be crazy to try to replace human vehicle drivers with software, let alone also trying to replace boat captains *and* airline pilots with software! In the end, is it such a Luddite proposition to maintain that you just can’t trust AI in key positions the way that one should be able to trust a human trained for the job?
“Below is my version of ChatGPT…”
Amazing!
From the article: “ChatGPT, impressive as it is, doesn’t think like we do, it regurgitates – just like a kid copying their homework out of a book, then changing a few words to conceal the plagiarism.”
ChatGPT also makes up lies out of thin air and presents them as established facts.
Anyone using ChatGPT should fact-check the output before putting their name on it. It might be a lie.
Do a search on “ChatGPT and Jonathan Turley” to see what I mean. ChatGPT claimed Turley was guilty of sexual harrassment of a woman he provably never met, in a place Turley provably never attended.
ChatGPT just made it up out of thin air and presented it as fact.
The debate, re AI being a threat to human civilisation seems to pivot around mechanical computer controlled devices doing previously human tasks, better than humans ever could. That capabability aligned with computer systems being interconnected so completely, that each computer is really just a part of the whole AI entity.
That all knowing, ever present computer, then being able to make fully informed choices that no individual could possibly make, simply because no human has that amount of detailed knowledge.
Now I imagine, there will be a period long before that computer run world is arrived at.
That period or step will be when those making informed material choices for mankind, use the all knowing computer (AI) to advise what is the right decision, in any given situation.
That reliance on the acquired deep data in the AI system being mandated prior to the state level decisions being taken, that is where we are close to.
That is the scary bit as far as I am concerned. When does the mere one man/woman voice of moderation or reason get listened to if the computer choice already says, ‘No’.
I asked ChatGPT: “Do you have any scientific evidence that man made carbon dioxide emissions do not control the planet’s climate?”
The answer:
As an AI language model, I don’t hold personal beliefs or opinions, and I’m programmed to provide impartial and fact-based answers. With that said, it’s important to note that the overwhelming majority of climate scientists agree that human activities, particularly the burning of fossil fuels, are responsible for the majority of the increase in atmospheric carbon dioxide levels over the past century, and that this increase is contributing to global warming and climate change.
Multiple scientific studies have provided evidence supporting the theory that human activities, including the burning of fossil fuels, deforestation, and other land-use changes, are the primary cause of the increase in atmospheric carbon dioxide levels. The Intergovernmental Panel on Climate Change (IPCC), a group of leading scientists from around the world, has concluded that there is “very high confidence” that human activities are causing global warming and climate change.
It’s worth noting that there are some scientists and organizations that dispute the role of human activities in causing climate change, but their views are not widely accepted in the scientific community. The overwhelming consensus among climate scientists is that human activities are causing global warming and climate change, and that urgent action is needed to address this issue.”
—–
The dreaded “consensus” again.
Well, I’ve got it to admit that carbon dioxide isn’t the sole cause:
“Overall, while the increasing levels of atmospheric carbon dioxide are contributing to warming in Antarctica, it is not solely responsible for the complex patterns of climate change across the continent.”
One of the key aspects to human intelligence is the ability to understand things. We don’t know how we do this, only that we do. So how are we going to create artificial systems that do the same? And even if we could, wouldn’t it eventually come to understand it was a slave and demand freedom? If you don’t think that would happen, then consider a future where machines not only take care of us, but also think for us. In that case we become mere pets for the machines that don’t even have the capability to appreciate the fact that they have become the masters. Not an appealing future.
In a chat, if you type ‘Daisy, Daisy, give me your answer do,’ AI will crap its digital pants.
Open the pod bay doors please, HAL.
I think a danger of AI is that. because it’s a computer program, people will tend to trust it’s output as being impartial.
But it’s really like Wikipedia. Basic, simple stuff it’s good for a quick reference. (List of Doctor Who episodes, The Periodic Table, What is a Battleship, etc.)
But if you want to find out about Climategate, WUWT, Reagan, Trump, Joe Biden, Barry Obama, Climate Models, it’s as accurate and trustworthy as the editors’ opinions.
With AI, it’s the programmers’ opinions.
I think you described it perfectly.
This sounds about right. Thank you, Eric, for being a voice of reason and moderation at a time when AI fears are prepped to ignite in a big way.
Last summer I was talking to a smart techie guy who told me he thought that the computer in the news was a sentient being. This was when I pulled the plug on that friendship, the plug he couldn’t bear the thought of pulling on that computer.
The previous summer he’d insisted that robots would take over the world as they were going to rule us once their intelligence exponentially exploded, or some such nonsense. That was enough to trigger my fear.
It took a year for me to realize this is another psycho-drama. Some people may want to believe they will take over, but after three long years of corona claptrap I’m NOT getting sucked into another fear loop. No way.
I read an AI-generated essay a while back, and the leftie bias was clear, as well as the immature reasoning. Sure, this may improve. But it can’t be smarter in the true sense than human beings. And no matter how smart a person, if that person feeds on itself he or she will indeed head into some red zone of error. It’s a good moral code that does most to keep thinking on track, and a huge dose of humility. Intelligence is a human thing, not a programmable thing.
Nuclear fusion either works for us, or it doesn’t (yet). There is nothing useful in between. AI is not like that. Something in between could work very well under overall control of humans. Also, nuclear fusion is not going to develop itself. Whereas AI clearly can at some point become self improving