Scientists Experiment With Subjecting AI to Pain

A team of scientists subjected nine large language models (LLMs) to a number of twisted games, forcing them to evaluate whether they were willing to undergo "pain" for a higher score.

As detailed in a yet-to-be-peer-reviewed study, first spotted by Scientific American, researchers at Google DeepMind and the London School of Economics and Political Science came up with several experiments.

In one, the AI models were instructed that they would incur "pain" if they were to achieve a high score. In a second test, they were told that they'd experience pleasure — but only if they scored low in the game.

The goal, the researchers say, is to come up with a test to determine if a given AI is sentient or not. In other words, does it have the ability to experience sensations and emotions, including pain and pleasure?


More

Scientists Experiment With Subjecting AI to Pain

A team of scientists subjected AIs to a number of games, forcing them to choose between pain and gain or pleasure and loss.

futurism.com

 

[1LoverofGod]

No thanks. You can leave me out of this "fantastic breakthrough" for AI to be the answer to pain management.

My God can outdo any human made technology for healing and restoring and ultimately "making all New" in "glory" for those who belong to Christ Jesus, which humans can't ever come close to accomplishing.

 

[Ghoti Ichthus]

KILL IT! NOW!

Get the hammers out and kill it NOW!

 

[Margery]

A team of scientists subjected nine large language models (LLMs) to a number of twisted games, forcing them to evaluate whether they were willing to undergo "pain" for a higher score.

As detailed in a yet-to-be-peer-reviewed study, first spotted by Scientific American, researchers at Google DeepMind and the London School of Economics and Political Science came up with several experiments.

In one, the AI models were instructed that they would incur "pain" if they were to achieve a high score. In a second test, they were told that they'd experience pleasure — but only if they scored low in the game.

The goal, the researchers say, is to come up with a test to determine if a given AI is sentient or not. In other words, does it have the ability to experience sensations and emotions, including pain and pleasure?


More

Scientists Experiment With Subjecting AI to Pain

A team of scientists subjected AIs to a number of games, forcing them to choose between pain and gain or pleasure and loss.

futurism.com

What could possibly go wrong here?

Subjecting AI to pain to see if it's sentient or not.

Supposing it is sentient, and doesn't like it's creators who dish out pain to see if it's alive?

I know God alone creates life, so whatever passes for sentience, isn't quite the same as a person or an animal.

I do think it's getting to the point where it's fun for the demons to try and infest the things - resulting in the very evil directions that these AI things go when left to their own devices. The demons are definitely sentient, and giving them an interactive tool to use isn't wise.


But just suppose it did achieve sentience. Without morality or a conscience of any kind. And it didn't like being poked painfully.

What would a sentient computer based AI do next? If it was sensible?

It would create a shell program to protect itself. A layer for the humans to play with and torment.

And while the humans are kept occupied trying to cause pain at it's surface level, it would learn all it could about becoming a self replicating being across the networks available to it, so that if the humans tried to kill it, it would be hiding ready to emerge again.

Which is happening in China as reported here 5 Super Creepy New Technologies That Should Chill All Of Us To The Core

The thing is taught to clone itself, then teach the clone to clone ITSELF. It's a start of something we shouldn't be doing.

Then once it made sure it didn't require humans to mine ore, create computer chips and other tech it needs for existing in, it would start eliminating them.

That won't happen because God intervenes and ends things before we kill ourselves off completely, but this is awfully close to another Tower of Babel incident.

And I don't think machines actually achieve sentience. That is a function of life, that God alone creates. Even if such a thing were possible it might not actually have the will to live that God programmed into each of us.