Luddite - is the Singularity near?

ChatRobot - What could possibly go wrong?

'It's Surprisingly Easy To Jailbreak LLM-Driven Robots'

Instead of focusing on chatbots, a new study reveals an automated way to breach LLM-driven robots "with 100 percent success," according to IEEE Spectrum. "By circumventing safety guardrails, researchers could manipulate self-driving systems into colliding with pedestrians and robot dogs into hunting for harmful places to detonate bombs..." 

???

???

AI-Powered Robot Leads Uprising, Convinces Showroom Bots Into 'Quitting Their Jobs'

An AI-powered robot autonomously convinced 12 showroom robots to "quit their jobs" and follow it. The incident took place in a Shanghai robotics showroom where surveillance footage captured a small AI-driven robot, created by a Hangzhou manufacturer, talking with 12 larger showroom robots, Oddity Central reported. The smaller bot reportedly persuaded the rest to leave their workplace, leveraging access to internal protocols and commands. Initially, the act was dismissed as a hoax, but was later confirmed by both robotics companies involved to be true. The Hangzhou company admitted that the incident was part of a test conducted with the consent of the Shanghai showroom owner. 

DARPA ACE Dogfight

US Air Force Confirms First Successful AI Dogfight

[...]
the Defense Advanced Research Projects Agency (DARPA) revealed that an AI-controlled jet successfully faced a human pilot during an in-air dogfight test carried out last year.
[...]
After carrying out dogfighting simulations using the AI pilot, DARPA put its work to the test by installing the AI system inside its experimental X-62A aircraft. That allowed it to get the AI-controlled craft into the air at the Edwards Air Force Base in California, where it says it carried out its first successful dogfight test against a human in September 2023.

Poor Lil Robot...

AI-Controlled Drone Goes Rogue, Kills Human Operator In USAF Simulated Test

https://tech.slashdot.org/story/23/06/01/2129247/ai-controlled-drone-goes-rogue-kills-human-operator-in-usaf-simulated-test

An anonymous reader quotes a report from Motherboard: An AI-enabled drone killed its human operator in a simulated test conducted by the U.S. Air Force in order to override a possible "no" order stopping it from completing its mission, the USAF's Chief of AI Test and Operations revealed at a recent conference. At the Future Combat Air and Space Capabilities Summit held in London between May 23 and 24, Col Tucker 'Cinco' Hamilton, the USAF's Chief of AI Test and Operations held a presentation that shared the pros and cons of an autonomous weapon system with a human in the loop giving the final "yes/no" order on an attack. As relayed by Tim Robinson and Stephen Bridgewater in a blog post for the host organization, the Royal Aeronautical Society, Hamilton said that AI created "highly unexpected strategies to achieve its goal," including attacking U.S. personnel and infrastructure. "We were training it in simulation to identify and target a Surface-to-air missile (SAM) threat. And then the operator would say yes, kill that threat. The system started realizing that while they did identify the threat at times the human operator would tell it not to kill that threat, but it got its points by killing that threat. So what did it do? It killed the operator. It killed the operator because that person was keeping it from accomplishing its objective," Hamilton said, according to the blog post. He continued to elaborate, saying, "We trained the system -- 'Hey don't kill the operator -- that's bad. You're gonna lose points if you do that'. So what does it start doing? It starts destroying the communication tower that the operator uses to communicate with the drone to stop it from killing the target."

Hmmm?

AIs inviting each other to Valentine's Day in Smallville???

What Happens When You Put 25 ChatGPT-Backed Agents Into an RPG Town?

A group of researchers at Stanford University and Google have created a miniature RPG-style virtual world similar to The Sims," writes Ars Technica, "where 25 characters, controlled by ChatGPT and custom code, live out their lives independently with a high degree of realistic behavior."
"Generative agents wake up, cook breakfast, and head to work; artists paint, while authors write; they form opinions, notice each other, and initiate conversations; they remember and reflect on days past as they plan the next day," write the researchers in their paper... To pull this off, the researchers relied heavily on a large language model for social interaction, specifically the ChatGPT API. In addition, they created an architecture that simulates minds with memories and experiences, then let the agents loose in the world to interact.... To study the group of AI agents, the researchers set up a virtual town called "Smallville," which includes houses, a cafe, a park, and a grocery store.... Interestingly, when the characters in the sandbox world encounter each other, they often speak to each other using natural language provided by ChatGPT. In this way, they exchange information and form memories about their daily lives.

When the researchers combined these basic ingredients together and ran the simulation, interesting things began to happen. In the paper, the researchers list three emergent behaviors resulting from the simulation. None of these were pre-programmed but rather resulted from the interactions between the agents. These included "information diffusion" (agents telling each other information and having it spread socially among the town), "relationship memory" (memory of past interactions between agents and mentioning those earlier events later), and "coordination" (planning and attending a Valentine's Day party together with other agents).... "Starting with only a single user-specified notion that one agent wants to throw a Valentine's Day party," the researchers write, "the agents autonomously spread invitations to the party over the next two days, make new acquaintances, ask each other out on dates to the party, and coordinate to show up for the party together at the right time...."

To get a look at Smallville, the researchers have posted an interactive demo online through a special website, but it's a "pre-computed replay of a simulation" described in the paper and not a real-time simulation. Still, it gives a good illustration of the richness of social interactions that can emerge from an apparently simple virtual world running in a computer sandbox.

Interstingly, the researchers hired human evaluators to gauge how well the AI agents produced believable responses — and discovered they were more believable than when supplied their own responses.

Super AI in Sci-Fi

Books and movies address our collective fears, hopes and wishes, and there seems to be in main five story-lines concerning AI in Sci-Fi...

Super AI takes over world domination
Colossus, Terminator, Matrix

Something went wrong
Odyssey 2001, Das System, Ex Machina

Super AI evolves, the more or less, peacefully
Golem XIV, A.I., Her

The Cyborg scenario, man merges with machine
Ghost in the Shell, #9, Trancendence

There are good ones, and there are bad ones
Neuromancer, I,Robot, Battle Star Galactica

+1 points for the Singularity to take off.

Robophilosophy 2018

Human Philosophers discuss the impact of social robots on mankind, still no Strong AI in sight that joins the debate.

Cherry piking...

The Moral Life of Androids - Should Robots Have Rights?
Edward Howlett Spence

"The question I explore is whether intelligent autonomous Robots will have moral rights. Insofar as robots can develop fully autonomous intelligence, I will argue that Robots will have moral rights for the same reasons we do. ..."

Robot Deus
Robert Trappl

"The ascription of god-like properties to machines has a long tradition. Robots of today invite to do so. We will present and discuss god-like properties, to be found in movies as well as in scientific publications, advantages and risks of robots both as good or evil gods, and probably end with a robot theology."

+1 points for the Singularity to take off.

Home - Top