Calculations Suggest It’ll Be Impossible to Control a Super-Intelligent AI

Contact Your Elected Officials
Science Alert Header

The idea of artificial intelligence overthrowing humankind has been talked about for many decades, and in January 2021, scientists delivered their verdict on whether we’d be able to control a high-level computer super-intelligence. The answer? Almost definitely not.

The catch is that controlling a super-intelligence far beyond human comprehension would require a simulation of that super-intelligence which we can analyze. But if we’re unable to comprehend it, it’s impossible to create such a simulation.

Rules such as ’cause no harm to humans’ can’t be set if we don’t understand the kind of scenarios that an AI is going to come up with, suggest the authors of the 2021 paper. Once a computer system is working on a level above the scope of our programmers, we can no longer set limits.

“A super-intelligence poses a fundamentally different problem than those typically studied under the banner of ‘robot ethics’,” wrote the researchers.

“This is because a superintelligence is multi-faceted, and therefore potentially capable of mobilizing a diversity of resources in order to achieve objectives that are potentially incomprehensible to humans, let alone controllable.”

Part of the team’s reasoning comes from the halting problem put forward by Alan Turing in 1936. The problem centers on knowing whether or not a computer program will reach a conclusion and answer (so it halts), or simply loop forever trying to find one.

As Turing proved through some smart math, while we can know that for some specific programs, it’s logically impossible to find a way that will allow us to know that for every potential program that could ever be written. That brings us back to AI, which in a super-intelligent state could feasibly hold every possible computer program in its memory at once.

Any program written to stop AI harming humans and destroying the world, for example, may reach a conclusion (and halt) or not – it’s mathematically impossible for us to be absolutely sure either way, which means it’s not containable.

“In effect, this makes the containment algorithm unusable,” said computer scientist Iyad Rahwan, from the Max-Planck Institute for Human Development in Germany back in January.

The alternative to teaching AI some ethics and telling it not to destroy the world – something which no algorithm can be absolutely certain of doing, the researchers say – is to limit the capabilities of the super-intelligence. It could be cut off from parts of the internet or from certain networks, for example.

The recent study rejects this idea too, suggesting that it would limit the reach of the artificial intelligence â€“ the argument goes that if we’re not going to use it to solve problems beyond the scope of humans, then why create it at all?

If we are going to push ahead with artificial intelligence, we might not even know when a super-intelligence beyond our control arrives, such is its incomprehensibility. That means we need to start asking some serious questions about the directions we’re going in.

“A super-intelligent machine that controls the world sounds like science fiction,” said computer scientist Manuel Cebrian, from the Max-Planck Institute for Human Development. “But there are already machines that perform certain important tasks independently without programmers fully understanding how they learned it.”

“The question therefore arises whether this could at some point become uncontrollable and dangerous for humanity.”

The research was published in the Journal of Artificial Intelligence Research.

A version of this article was first published in January 2021.

By DAVID NIELD

Read Original Article on ScienceAlert.com

The Thinking Conservative
The Thinking Conservativehttps://www.thethinkingconservative.com/
The goal of THE THINKING CONSERVATIVE is to help us educate ourselves on conservative topics of importance to our freedom and our pursuit of happiness. We do this by sharing conservative opinions on all kinds of subjects, from all types of people, and all kinds of media, in a way that will challenge our perceptions and help us to make educated choices.

The Choices We Make

Death and disagreement are inevitable. Love and hate are choices. We will all die. Before we do, what choices will we make?

Elon Musk Speaks at Unite the Kingdom Rally

Tommy Robinson held rally, with Elon Musk appearing virtually, calling attention to leftist politicians who allow foreign immigrants to invade England.

Doxed Democrats Are Getting Fired Left and Left

Not a misprint because a title of “left and...

Hold Up, Feds, Without Federalism, There Is No USA

Federalism is essential to governing the U.S., yet the federal government is undermining it by bribing states to implement unnecessary federal programs.

A Widow Inspires The World

Erika Kirk moved the nation with her speech two days after her husband’s assassination, vowing to continue his mission and grow Turning Point USA.

Parents Sue Character.AI for Allegedly Leading Kids to Sexual Abuse, Suicidal Behavior

Parents allege in three lawsuits that Character.AI’s chatbots sexually abused their children and drove them toward suicidal thoughts and behavior.

Tyler Robinson Makes First Appearance in Court, Faces Capital Murder Charge in Charlie Kirk Assassination

Tyler Robinson remained motionless throughout his first court appearance on capital murder and other charges after the shooting death of Charlie Kirk.

Trump to Appeal Ruling Allowing Fed Governor Lisa Cook to Keep Her Job

The Trump admin will appeal a three-judge panel’s ruling that prevents the president from firing Federal Reserve Governor Lisa Cook.

Charlie Kirk’s Alleged Murderer Confessed Shortly After Shooting, Messages Show

The man accused of murdering conservative influencer Charlie Kirk confessed to the killing in text messages, authorities said on Sept. 16.

Rubio Says US Visa Revocations Underway After Charlie Kirk Death Celebrations

SoS Marco Rubio said foreign nationals who made celebratory comments over Charlie Kirk’s assassination will have their U.S. visas revoked.

Trump Supports Designating Antifa a Terrorist Organization

President Trump said he would support designating the antifa movement a terrorist organization in the wake of Charlie Kirk’s assassination last week.

US Conducts Strike on Another Drug Boat From Venezuela: Trump

Three people were killed in a U.S. strike on a Venezuelan drug boat, President Donald Trump announced on Sept. 15.

Trump Signs Memo Targeting Direct-to-Consumer Pharmaceutical Advertising

President Trump signed a memo to ensure drug ads give fair, balanced, and complete information to protect and inform American consumers.
spot_img

Related Articles

Popular Categories

MAGA Business Central