Daily Dose of Doom Thread

[MU Fan in Connecticut]

This can't be good.

https://twitter.com/Billyhottakes/status/1593307410684313603?s=20&t=iEey1ZF5jmvy4tXNjUwQhw

Dad has to vacuum the pool.....Its reaaaalllll dirty.

[MU82]

From the NYT:

Social media’s newest star is a robot: a program called ChatGPT that tries to answer questions like a person.

Since its debut last week, many people have shared what the bot can do. New York magazine journalists told it to write what turned out to be a “pretty decent” story. Other users got it to write a solid academic essay on theories of nationalism, a history of the tragic but fictitious Ohio-Indiana War and some jokes. It told me a story about an artificial intelligence program called Assistant that was originally set up to answer questions but soon led a new world order that guided humanity to “a new era of peace and prosperity.”

What is remarkable about these examples is their quality: A human could have written them. And the bot is not even the best; OpenAI, the company behind ChatGPT, is reportedly working on a better model that could be released next year.

“A lot of the promised benefits of A.I. have been eternally five years away,” my colleague Kevin Roose, who covers technology, told me. “ChatGPT was a moment when a technology people had heard about finally became real to them.”

In today’s newsletter, I’ll explain the potential benefits of artificial intelligence but also why some experts worry it could be dangerous.

The upside of artificial intelligence is that it might be able to accomplish tasks faster and more efficiently than any person can. The possibilities are up to the imagination: self-driving and even self-repairing cars, risk-free surgeries, instant personalized therapy bots and more.

The technology is not there yet. But it has advanced in recent years through what is called machine learning, in which bots comb through data to learn how to perform tasks. In ChatGPT’s case, it read a lot. And, with some guidance from its creators, it learned how to write coherently — or, at least, statistically predict what good writing should look like.

There are already clear benefits to this nascent technology. It can help research and write essays and articles. ChatGPT can also help code programs, automating challenges that can normally take hours for people.

Another example comes from a different program, Consensus. This bot combs through up to millions of scientific papers to find the most relevant for a given search and share their major findings. A task that would take a journalist like me days or weeks is done in a couple minutes.

These are early days. ChatGPT still makes mistakes, such as telling one user that the only country whose name starts and ends with the same letter is Chad. But it is very quickly evolving. Even some skeptics believe that general-use A.I. could reach human levels of intelligence within decades.

Despite the potential benefits, experts are worried about what could go wrong with A.I.

For one, such a level of automation could take people’s jobs. This concern has emerged with automated technology before. But there is a difference between a machine that can help put together car parts and a robot that can think better than humans. If A.I. reaches the heights that some researchers hope, it will be able to do almost anything people can, but better.

Some experts point to existential risks. One survey asked machine-learning researchers about the potential effects of A.I. Nearly half said there was a 10 percent or greater chance that the outcome would be “extremely bad (e.g., human extinction).” These are people saying that their life’s work could destroy humanity.

That might sound like science fiction. But the risk is real, experts caution. “We might fail to train A.I. systems to do what we want,” said Ajeya Cotra, an A.I. research analyst at Open Philanthropy. “We might accidentally train them to pursue ends that are in conflict with humans’.”

Take one hypothetical example, from Kelsey Piper at Vox: A program is asked to estimate a number. It figures out that the best way to do this is to use more of the world’s computing power. The program then realizes that human beings are already using that computing power. So it destroys all humans to be able to estimate its number unhindered.

If that sounds implausible, consider that the current bots already behave in ways that their creators don’t intend. ChatGPT users have come up with workarounds to make it say racist and sexist things, despite OpenAI’s efforts to prevent such responses.

The problem, as A.I. researchers acknowledge, is that no one fully understands how this technology works, making it difficult to control for all possible behaviors and risks. Yet it is already available for public use.

[mu_hilltopper]

ChatGPT is incredible. 

I've done a bunch of them, and the results just blow my mind.

Example:  "Write a scene from Knight Rider where KITT uses his rockets to jump over a building"

Output:

Michael and KITT were speeding down the highway, hot on the tail of a group of criminals. The criminals had stolen a truck full of valuable technology, and Michael and KITT were determined to stop them.

"KITT, we need to catch up to that truck," said Michael. "Can you use your rocket boosters to jump over that building and cut them off?"

"Affirmative, Michael," said KITT. "Activating rocket boosters now."

KITT accelerated, shooting towards the building at top speed. As he reached the edge, he deployed his rocket boosters, launching himself into the air.

Michael watched in amazement as KITT soared over the building, landing smoothly on the other side. The criminals were caught off guard, and KITT quickly overtook them, bringing the truck to a stop.

"Nice work, KITT," said Michael, as he jumped out of the car and arrested the criminals. "You never cease to amaze me."

"It is my pleasure to serve, Michael," said KITT. "Together, we make a formidable team."

It's just incredible that .. It's one thing to be able to google a 40 year old TV show and know the characters .. it's another to write a script that's . .pretty damn close to what you'd see on TV.

It's astonishing stuff.  I doubt my kids will ever write an essay before asking the AI to do it for them.   

[mu_hilltopper]

WE Energies is asking everyone to turn their thermostats down to 60-62F to avoid a massive natural gas disruption.

Perfect doom storm, coldest day of the year, holiday.

https://www.wisn.com/article/wisonsin-gas-supply-affected-damaged-pipeline-we-energies/42331657

[PointWarrior]

"Take one hypothetical example, from Kelsey Piper at Vox: A program is asked to estimate a number. It figures out that the best way to do this is to use more of the world’s computing power. The program then realizes that human beings are already using that computing power. So it destroys all humans to be able to estimate its number unhindered."


Please explain to me how an AI program will destroy all humans....

[TSmith34, Inc.]

Matthew Broderick knows how.

[warriorchick]

Matthew Broderick knows how.

Also, Sarah Connor.

[MU82]

Also, almost every human on Discovery One.

[ZiggysFryBoy]

https://madison365.com/indigenous-arts-leader-activist-revealed-as-white/

It's the end of the world as we know it, and I feel fine.  🎶🎶🎶🎶

[The Hippie Satan of Hyperbole]

https://madison365.com/indigenous-arts-leader-activist-revealed-as-white/

It's the end of the world as we know it, and I feel fine.  🎶🎶🎶🎶

Done in by a relative's genealogy site...

[JWags85]

https://madison365.com/indigenous-arts-leader-activist-revealed-as-white/

It's the end of the world as we know it, and I feel fine.  🎶🎶🎶🎶

(laughs in Rachel Dolezal)

I also like that she didn't just choose one Native American tribe, maybe give herself a way out, no she chose FOUR.  Plus Cuban AND Jewish.

Even funnier was "I am still processing it all" aka I need to figure out how to wriggle out of being caught red handed and continue to grift somehow.

[tower912]

Went full Santos?

[ZiggysFryBoy]

Went full Santos?

Santos didn't pretend to be a multi-tribal, non-binary, Cuban Jew that stole other indigenous artists' work. (ok, maybe the Jew thing)

Elizabeth Warren would be a better example.

[Uncle Rico]

Santos didn't pretend to be a multi-tribal, non-binary, Cuban Jew that stole other indigenous artists' work. (ok, maybe the Jew thing)

Elizabeth Warren would be a better example.

He might be house leader

[TSmith34, Inc.]

Santos didn't pretend to be a multi-tribal, non-binary, Cuban Jew that stole other indigenous artists' work. (ok, maybe the Jew thing)

Yeah, with slight variations he really kind of did.

Thank goodness he survived brain cancer and can serve NY in the House.

[ZiggysFryBoy]

He might be house leader

Good for him.  The gift paid off.

[Uncle Rico]

Water issues in the southwest continue

https://www.yahoo.com/news/skipped-showers-paper-plates-arizona-130945292.html

[mu_hilltopper]

https://www.reddit.com/r/Damnthatsinteresting/comments/10gcitd/a_machine_gun_integrated_with_a_robot_dog/

[ZiggysFryBoy]

https://www.reddit.com/r/Damnthatsinteresting/comments/10gcitd/a_machine_gun_integrated_with_a_robot_dog/

This is masterbation material for Nads for at least 5 days.

[The Hippie Satan of Hyperbole]

https://www.reddit.com/r/Damnthatsinteresting/comments/10gcitd/a_machine_gun_integrated_with_a_robot_dog/

Best comment: "I love how the tippy tapping legs make it seem so happy about shooting things."

[rocket surgeon]

Water issues in the southwest continue

https://www.yahoo.com/news/skipped-showers-paper-plates-arizona-130945292.html

Maybe this will help alleviate some of your concerns there reeeek, unless your stuff from yahoo was just part of your ongoing relentless, but oh so hilarious schticks

https://www.phoenix.gov/waterservices/resourcesconservation/drought-information/climatechange/water-supply-q-a

[cheebs09]

https://www.reddit.com/r/Damnthatsinteresting/comments/10gcitd/a_machine_gun_integrated_with_a_robot_dog/

USPS is on notice.

[real chili 83]

https://www.reddit.com/r/Damnthatsinteresting/comments/10gcitd/a_machine_gun_integrated_with_a_robot_dog/

That would fix Muggsy's polar bear problem.

[Plaque Lives Matter!]

Maybe this will help alleviate some of your concerns there reeeek, unless your stuff from yahoo was just part of your ongoing relentless, but oh so hilarious schticks

https://www.phoenix.gov/waterservices/resourcesconservation/drought-information/climatechange/water-supply-q-a

Arizona has junior rights to basically everyone else on the Colorado river so they will be the first to be cut off when the supply dwindles. Phoenix has more people so will be in better shape than Arizona farmers but the situation being “optimal” is just salesmanship on the area itself. The same reason LA would be prioritized over Phoenix - more people. If the Central Arizona Project is restricted/cut off. That’s very bad news for the state.

[Uncle Rico]

Maybe this will help alleviate some of your concerns there reeeek, unless your stuff from yahoo was just part of your ongoing relentless, but oh so hilarious schticks

https://www.phoenix.gov/waterservices/resourcesconservation/drought-information/climatechange/water-supply-q-a

I’m not concerned.  I’m not dumb enough to live there