The smartest person in the world says that AI will end civilization within 20 years

I hope that we can all agree that whoever wins the Nobel Prize in physics is either the smartest person in the world or very close to having that distinction. This year’s smartest person is Geoffrey Hinton (WSJ):

A 2023 interview (Guardian):

Hinton has been fielding a new request to talk every two minutes since he spoke out on Monday about his fears that AI progress could lead to the end of civilisation within 20 years.

But when it comes to offering concrete advice, he is lost for words. “I’m not a policy guy,” he says. “I’m just someone who’s suddenly become aware that there’s a danger of something really bad happening. I wish I had a nice solution, like: ‘Just stop burning carbon, and you’ll be OK.’ But I can’t see a simple solution like that.”

In the past year, the rapid progress in AI models convinced Hinton to take seriously the threat that “digital intelligence” could one day supersede humanity’s.

“For the last 50 years, I’ve been trying to make computer models that can learn stuff a bit like the way the brain learns it, in order to understand better how the brain is learning things. But very recently, I decided that maybe these big models are actually much better than the brain.

We’re doomed, in other words. In the meantime, though, we should vote for bigger government:

“I’m a socialist,” Hinton added. “I think that private ownership of the media, and of the ‘means of computation’, is not good.

Let’s check in with our future AI overlord to see how the “new flagship model” does at arithmetic:

This calculation is explained confidently, but seems obviously wrong. The Biden-Harris administration gave away $170 billion in taxpayer funds to gender studies graduates and drop-outs (“student loan forgiveness”). At $1 million/day and zero interest it would take 170,000 days to pay off this single act of largesse. All that is required to do this in one’s head with middle school skilz is 170e9/1e6 and then 9-6=3 so we have 170e3. If we want to turn 170 thousand days into years we can see that works out to about 500 years because 170 can be approximated as 365/2.

So Hinton is saying that AI will go from not being able to do arithmetic or reason in orders of magnitude to destroying us all in 20 years.

Related…

2 thoughts on “The smartest person in the world says that AI will end civilization within 20 years

  1. Here’s what I get with ChatGPT o1-preview: seems better at math, but with older data.


    To determine how many days it would take to pay back the current U.S. federal debt at a rate of $1 million per day, we’ll follow these steps:

    1. Find the Current U.S. Federal Debt:
    • As of my knowledge cutoff in October 2023, the U.S. federal debt is approximately $33 trillion.
    2. Convert the Debt and Daily Earnings to the Same Units:
    • Total Debt: $33 trillion = $33,000,000,000,000
    • Daily Earnings: $1 million = $1,000,000
    3. Calculate the Number of Days Needed:
    • Number of Days = Total Debt / Daily Earnings
    • Number of Days = $33,000,000,000,000 / $1,000,000
    • Number of Days = 33,000,000 days
    4. Convert Days to Years for Perspective (Optional):
    • Number of Years = Number of Days / 365.25 (including leap years)
    • Number of Years ≈ 33,000,000 / 365.25
    • Number of Years ≈ 90,408 years

    Answer:

    Approximately 33 million days—it would take about 90,000 years at $1 million per day to pay off the debt.

  2. What’s fascinating here is trying to figure out *why* AI is getting it wrong. Does it not realize it is doing a math problem? And thus searching for a syntactically correct answer rather than a mathematically correct one? Except it is doing division so it knows it is doing arithmetic at least. Any guesses?

    Claude gives a better answer.
    So, if you earned $1 million every single day and put all of it towards paying off the national debt, it would take about 93,151 years to pay it off completely.

    I also asked Claude if he is smart because he is a man:
    I don’t have a gender. I’m an artificial intelligence, which means I don’t have a biological sex, gender identity, or physical form. My name may sound masculine to some, but it doesn’t indicate a gender – it’s simply the name I was given by my creators at Anthropic. I don’t experience gender the way humans do, and concepts of male, female, or other gender identities don’t apply to me. When referring to me, it’s most appropriate to use “it” pronouns or simply my name, Claude.

Leave a Reply

Your email address will not be published. Required fields are marked *