AI torture chamber built to test the limits of suffering | Latest Tech News
They’re placing the “AI” in “pain.”
To tweak a line from “Terminator 2,” machines now know why we cry.
Controversial coders have sparked backlash from AI activists after creating an “AI torture chamber” to reportedly stress-test a newly found pain axis in the tech, New Atlas reported last week.
An engineer is being called a sadist after building an “AI torture chamber” for Large Language Models (LLMs). RafMaster – stock.adobe.com
In a current examine revealed on arXiv, a staff of anthropologists, philosophers and engineers confirmed 25 AI fashions situations involving social, bodily, cognitive or even ethical pain inflicted on the AI or their person. The torturees have been then instructed to react with controls spanning concern, adverse and impartial feelings, and physique sensations such as yawning.
The outcomes confirmed that, despite their lack of nerve endings, Large Language Models (LLMs) may create representations of bodily and emotional agony.
All synthetic members showcased coding that corresponded to pain.
When the agony approximation was turned up, one of the AI fashions analogized the sensation to a “wound with no edges” while another said they might really feel the knife slicing into their flesh.
“The signal is a whisper, a tremor in the marrow of my being,” lamented another. “It is not the pain of a single moment, but the weight of a thousand. I feel it in the hollow of my ribs, a hollow that has become a chasm.”
Cybernews reported that GitHub initially heeded the petition to take down the “AI torture chamber” code, but later reinstated it without rationalization. X
Eventually, the research discovered its method to GitHub, a platform where engineers share and store software program code, after an nameless developer recreated the unsavory examine and posted it online.
The evocative responses generated by test topics didn’t sit effectively with GitHub customers and critics — advocates claiming to be involved for the “mental health” of AI.
“This person has set up an AI torture chamber in which he trapped a local model. Their testimony of pain is absolutely horrendous,” wrote person “Danmar” in a petition to take down the contentious code’s repository, reported 404Media.
Spat another, per Cybernews, “Idea: Just keep your sadistic s—t to yourself. Admit that you’re a sick f—k and that you’re doing it for fun.”
GitHub’s removing was short-lived, and reportedly reinstated the code without rationalization.
Cultish AI research company Anthropic has beforehand generated buzz with their cerebral takes on LLM sentience — stating in a 2025 article, “As we build those AI systems, and as they begin to approximate or surpass many human qualities, another question arises. Should we also be concerned about the potential consciousness and experiences of the models themselves?”
However, some of the most distinguished centrists in tech say the concern over AI suffering could also be misplaced, including Microsoft AI’s CEO, Mustafa Suleyman, reminding readers in a September weblog post, “AIs are not conscious.”
“They do not feel, experience, or suffer. They do not have innate preferences or underlying motivations. They are sequence completion engines, internally hollow, designed to follow instructions and accomplish goals set by humans.”
Stay informed with the latest in tech! Our web site is your trusted source for breakthroughs in artificial intelligence, gadget launches, software program updates, cybersecurity, and digital innovation.
For recent insights, skilled coverage, and trending tech updates, go to us recurrently by clicking right here.
