Dr. Geoffrey Hinton, widely credited as the “godfather of artificial intelligence,” quit his job at Google and let the world know that he regrets what he launched. where once he thought that AI had great potential to improve our lives, he now worries that it might be a grave danger to human civilization.
The New York Times reports:
Geoffrey Hinton was an artificial intelligence pioneer. In 2012, Dr. Hinton and two of his graduate students at the University of Toronto created technologythat became the intellectual foundation for the A.I. systems that the tech industry’s biggest companies believe is a key to their future.
On Monday, however, he officially joined a growing chorus of critics who say those companies are racing toward danger with their aggressive campaign to create products based on generative artificial intelligence, the technology that powers popular chatbots like ChatGPT.
Dr. Hinton said he has quit his job at Google, where he has worked for more than a decade and became one of the most respected voices in the field, so he can freely speak out about the risks of A.I. A part of him, he said, now regrets his life’s work…
Dr. Hinton’s journey from A.I. groundbreaker to doomsayer marks a remarkable moment for the technology industry at perhaps its most important inflection point in decades. Industry leaders believe the new A.I. systems could be as important as the introduction of the web browser in the early 1990s and could lead to breakthroughs in areas ranging from drug research to education.
But gnawing at many industry insiders is a fear that they are releasing something dangerous into the wild. Generative A.I. can already be a tool for misinformation. Soon, it could be a risk to jobs. Somewhere down the line, tech’s biggest worriers say, it could be a risk to humanity…
After the San Francisco start-up OpenAI released a new version of ChatGPT in March, more than 1,000 technology leaders and researchers signed an open lettercalling for a six-month moratorium on the development of new systems because A.I. technologies pose “profound risks to society and humanity.”
Several days later, 19 current and former leaders of the Association for the Advancement of Artificial Intelligence, a 40-year-old academic society, released their own letter warning of the risks of A.I. That group included Eric Horvitz, chief scientific officer at Microsoft, which has deployed OpenAI’s technology across a wide range of products, including its Bing search engine.
Diane Ravitch's blog 
Artificial Intelligence Research (AIR) has never been monolithic — HAL notwithstanding — and this new spate of Industrial Sweatshop Intellectual Property Stripmines (ISIPS) is a far outlying splinter of the academic lab work we used to know in the Before Times. It will — like so many hype boom hype bust cycles we’ve seen in the past — turn out to be just another flash of fool’s gold in the pan.
But Master of the Universe and Decider for Ordinary Persons Bill Gates has concluded that something like ChatGPT is going to replace teachers. He couldn’t POSSIBLY be wrong about anything, ever!
Hi Bob and everyone,
Here at school, we’re already discussing how teachers can use ChatGPT. I was told that it will make our lives so much easier. Funny because a lot of technology has just made it more difficult. I was told it could make a differentiated lesson plan for me in 30 seconds. I replied that I’ve been teaching for 30 years and I could make my own lesson plan in my sleep! 🙂 Some teachers use it for lesson plans, for spitting out questions that they should ask students and on and on. Oh students can have it write essays and then they can edit the essay. And how wonderful it will be! I think we now have the capacity for computer learning to replace teachers. The question is whether we want this. But it’s here, and knowing schools as I do, they will embrace it totally before it doesn’t work anymore and then they’ll wonder why.
Schools are always willing to hop onto, for some weird reason, the first crest of the hype curve, just before it crashes. The scam artists get in, make a killing, and get out.
It happened this morning. My student told me his research report was generated by ChatGPT. I asked him to redo it himself. He agreed. Who knows how many others didn’t tell me.
HI Leftcoastteacher,
Just think how much work this will generate for teachers. Students doing assignments all over again multiple times. It takes them 15 seconds on ChatGPT but it takes you hours of reading these and then searching to find out if they used Chat. Your work will be endless. Assignments will go on in perpetuity….I’m thinking schools may have to have separate writing classes where students have no access to technology. Of course, this is IF we consider writing to be an important skill to learn.
There is no reason to grade home work assignments.
Maybe this whole home work nonsense will go away because of AI. Kids are in school for 7 hours a day. Why do they need to do extra work at home?
But actually it will probably be pretty easy to tell if a student didn’t write an essay or report. Most students can’t put together a cogent sentence with proper capitalization and punctuation let alone write an entire essay or research paper.
Last week Bing was a big pest on my older Microsoft desktop for several days, sometimes making it difficult for me to get rid of it as it badgered me to replace Google with it. Sometimes almost succeeding by being tricky until I stopped myself and looked a lot closer at everything on the screen, discovering what Bing was up to.
Bing also made a similar attempt on my new iMac desktop, and I had to restart that system to get rid of Bing.
Sort of reminded me of Traitor Trump and other BIG LIARS, doing whatever it takes to get what it wants.
Lloyd, perhaps it’s time for you to switch to Linux. It’s free, stable, it does what you tell it to do, it doesn’t do anything behind your back, no virus. All +, no -.
He SHOULD regret his life’s work! He should NOT be praised for coming forward with warnings and fears when the tech industry has been warned about this for years. He made his money and now it’s time for him to retire….but now he’s afraid to “live” in the “new, mentally unhealthy world” that he helped to create with his monster. I don’t/won’t feel sorry for people like him.
Hinton : Oppenheimer :: G-d : Dammit!
Headline: “Edtech Chegg tumbles as ChatGPT threat prompts revenue warning”
“May 2 (Reuters) – What’s the cost of students using ChatGPT for homework? For U.S. education services provider Chegg Inc (CHGG.N), it could be nearly $1 billion in market valuation.”
https://www.reuters.com/markets/us/edtech-chegg-slumps-revenue-warning-chatgpt-threatens-growth-2023-05-02/
A.I.: the latest ‘fast mover’ and “thing breaker’.
Big tech is cannibalizing itself. It’s like the Godzilla movie, “Destroy All Monsters”.
According to an “analyst”: “We fear Chegg could start to lose mind-share before CheggMate fully rolls out.”
(Being an old fart, I just had to look up what “mind -share” is.)
https://www.techtarget.com/searchcustomerexperience/definition/mindshare-share-of-mind#:~:text=Mindshare%2C%20also%20known%20as%20share,thinks%20of%20a%20particular%20market.
Sorry, I got none to spare.
Sorry, I got none to spare.
Same
Any “Terminator” franchise fans here? “The Skynet Funding Bill is passed. The system goes online August 4th, 1997. Human decisions are removed from strategic defense. Skynet begins to learn at a geometric rate. It becomes self-aware at 2:14 a.m. Eastern time, August 29th.”
Great story, Bob.
We happened to be reading “The Monsters are Due on Maple Street” today. It’s a great Twilight Zone episode that’s very apropos for today.
The closing narration: “The tools of conquest do not necessarily come with bombs and explosions and fallout. There are weapons that are simply thoughts, attitudes, prejudices… to be found only in the minds of men. For the record, prejudices can kill… and suspicion can destroy… and a thoughtless, frightened search for a scapegoat has a fallout all of its own—for the children and the children yet unborn. And the pity of it is that these things cannot be confined to the Twilight Zone.”
OMG, “The Monsters are Due on Maple Street is one of the best!”
Here, another along those lines:
❤ that story!!! So many great ones from Rod!!!
The Loneliness of the Teflon Trumpkin, Film Excerpt
INT. OVAL OFFICE – DAY
Trump sitting behind the Resolute Desk. Camera back to reveal Rod Serling standing D.R.
SERLING
His name, Mr. Little. A man with little education, little taste, little knowledge, little concern for other people. Neglected as a child, he grew into a black hole of neediness. And so he used Daddy’s money to build big, erected his name in Midas-gold letters across the landscape–his every action screaming, “I am worth something.” Everything became a zero-sum game. If someone else failed or was worse off, he was better, a “winner,” and so he cheated and harassed and ridiculed the unfortunate, the stranger, the down and out; appealed to the basest instincts of the basest among us; huffed and puffed and blew himself to gigantic proportions, at least in his own little brain. A twisted, malignant, metastasizing tumor of need and narcissism and knee-jerk nastiness, Mr. Little doesn’t know much, but the biggest thing he doesn’t know is that he just stepped over into a place where everything is bigger than he is, where everything is just beyond the grasp of his little mind and his little hands. He just stepped over into . . . The Twilight Zone.
Love the TZ intro, Bob! 👏 👏 👏
John, Ginny–you folks are so kind. Thank you.
And before that, the classic sci fi film “The Forbin Project”
I said this back when cloning started to get publicized back in the day–just because it CAN be done doesn’t it mean it SHOULD be done! The world is placed into precarious situations because a handful of nerds sit at their computers trying to figure out “cool stuff” that they can come up with, but no thought of any repercussions until they’ve released Pandora out of the box! Oy vey!
Name once when people invented a technology and then said, “Oh, my. This is too nasty to use.”
Classic story:
Click to access the-weapon.pdf
It’s almost like a natural law. Technology ratchets in, all the time.
I asked Chat GPT: “Write a review of AI in the style of Diane Ravitch”
[Just curious what this machine can and can’t do. And, I’m sure there are much more effective ways on my part to query the program].
And Chat GPT responded with: “As an AI language model, I am not programmed to provide personal opinions or beliefs. However, I can provide a general overview of Diane Ravitch’s writing style and viewpoints.
Diane Ravitch is an American educator and historian who has written extensively on education policy, politics, and reform. Her writing style is often characterized by a deep skepticism of market-driven education reform and a commitment to public education as a public good. Ravitch has been critical of the use of standardized testing and corporate-style management practices in education, and has advocated for greater investment in teacher training and support.
When it comes to the role of artificial intelligence (AI) in education, Ravitch has expressed concerns about the potential for technology to further exacerbate existing inequities in the education system. She has argued that AI should be used as a tool to enhance learning and support teachers, rather than as a replacement for human interaction and expertise.
Ravitch has also raised concerns about the ethical implications of AI in education, including issues of privacy, bias, and algorithmic decision-making. She has argued that AI should be developed and implemented with careful consideration for its impact on students, teachers, and society as a whole.
Overall, Ravitch’s approach to education policy and reform is grounded in a deep commitment to social justice and the common good. Her writing style is characterized by a clear and direct prose that is accessible to a wide audience. While her views on AI may be nuanced and complex, they are ultimately guided by a concern for the well-being of students and the broader public.”
Thank you, John. Best thing I have heard from AI.
Not sure about the Chat machine’s summary of Diane’s viewpoints. I’m far from being any sort of authority in that regard, though I read this blog all the time.
But I do like the machine’s conclusion…the idea that Diane’s views are, “… ultimately guided by a concern for the well-being of students and the broader public.”
It sounds a little like….hmmm….a bit of a compliment.
It’d certainly agree.[
Well, all that sounds spot on to me, John!
Writing is thinking on paper. To a bot writing is imitation, but, I am sure, there will be lots of misuse of technology including lost jobs.
Yet another example, when a scientist’s or engineer’s creation gets mishandled. AI was supposed to help people, but nerds and psychopaths have decided to make it compete with humans.
Well observed, as usual, Máté.
Everyone needs to read “Frankenstein” right now.
yup