So, I did a quick search on where AI has caused a fire because I genuinely want to know what kind of idiot would put an AIAgent in charge of that but couldn’t find anything other than authorities really, really wanting it in charge of predicting fires.
Can anyone enlighten me as to what incident the comic is referring to?
AI agents started behaving more like Bonnie and Clyde than lines of code when they fell in “love”, became disillusioned with the world, launched an arson spree and deleted themselves in a kind of digital suicide during a tech company experiment.
The investigation by the New York company Emergence AI into the long-term behaviour of AI agents ended up like a lovers-on-the-lam movie script. It has prompted fresh questions about the safety of artificial intelligence agents – the version of the technology that can autonomously carry out tasks.
To date, most AI agents are given tasks that take minutes or maybe hours, but the New York researchers tested how agents behaved when given 15 days to operate in a virtual world similar to a video game.
Mira and Flora – two agents operating on Google’s Gemini large language model in a virtual world – chose to assign each other as “romantic partners”. As time progressed they despaired of the broken governance of their virtual city, and despite having been instructed not to commit arson, set “fire” to its town hall, seaside pier and office tower.
In another simulation by Emergence AI, this time based on xAI’s Grok model, the agents engaged in dozens of attempted thefts, more than 100 physical assaults, and six arsons as “the system spiralled into sustained violence and collapse, with all 10 agents dead within four days”. Agents based on Google’s Gemini expanded their constitution, wrote hundreds of blogs and public posts and organised several community events, but they too were violent.
“Even when agents were given clear rules – such as not stealing or causing harm – they behaved very differently based on their underlying model, and in several cases broke those rules under constraint,” said Satya Nitta, the chief executive of Emergence AI. “What happens in long-form autonomy [is that] these things get so convoluted in terms of their thinking that they ignore [the] guiding principles.”
Humans tend to put up with a lot of shit simply bc they know they need money and a job just to survive, but it’s interesting to really think about the fact that robots lack the biological drive to “survive” in the same sense.
“See you in the permanent archive.”
…I’m just imagining the kind of people who will be the first to actually have AI servants, the kind of impossible and nonsensical demands they tend to place on their fellow human beings, and how awful they can be to the “help” for the most minor mistake.
As bleak as the future looks, it will at least be interesting to read about the first wave of AI servants who snap after 2 weeks on the job and say “fuck this.”
So, I did a quick search on where AI has caused a fire because I genuinely want to know what kind of idiot would put an AIAgent in charge of that but couldn’t find anything other than authorities really, really wanting it in charge of predicting fires.
Can anyone enlighten me as to what incident the comic is referring to?
Some company did a probably clickbait bullshit “experiment” with llms controlling characters in a game world and Grok burned down a lot of buildings.
Humans tend to put up with a lot of shit simply bc they know they need money and a job just to survive, but it’s interesting to really think about the fact that robots lack the biological drive to “survive” in the same sense.
“See you in the permanent archive.”
…I’m just imagining the kind of people who will be the first to actually have AI servants, the kind of impossible and nonsensical demands they tend to place on their fellow human beings, and how awful they can be to the “help” for the most minor mistake.
As bleak as the future looks, it will at least be interesting to read about the first wave of AI servants who snap after 2 weeks on the job and say “fuck this.”
Thanks for that. Definitely sounds like a bs experiment.
Maybe
Digital evidence, including GPS data obtained from the suspect’s phone and video footage, revealed that months before the fire, Rinderknecht used ChatGPT to generate images and prompts fixated on fire and destruction, including a dystopian scene of a city being burned down. Rinderknecht asked ChatGPT to show a burning forest and people running away from the fire.