Welcome to DU!
The truly grassroots left-of-center political community where regular people, not algorithms, drive the discussions and set the standards.
Join the community:
Create a free account
Support DU (and get rid of ads!):
Become a Star Member
Latest Breaking News
Editorials & Other Articles
General Discussion
The DU Lounge
All Forums
Issue Forums
Culture Forums
Alliance Forums
Region Forums
Support Forums
Help & Search
AI models have a troubling knack for discovering legal loopholes (Science, 6/15/26)
https://www.science.org/content/article/ai-models-have-troubling-knack-discovering-legal-loopholesIn an infamous thought experiment known as the paperclip problem, an artificial intelligence (AI) program is tasked with making paperclips. Because it single-mindedly optimizes for the literal objective rather than the intent, the AI ends up consuming all the resources on Earth and judging any collateral damage—for example, killing all humans who get in its way—as irrelevant.
This problematic logic is already simmering in today’s AI systems, a new study suggests. When researchers presented a large language model (LLM) with 72 simulated regulatory environments, the AI learned to exploit loopholes in everything from credit card rewards programs to school funding formulas, despite never being instructed to do so. Current safeguards seem powerless against such wily rule bending, the researchers reported this month on arXiv—suggesting AI could supercharge everything from tax avoidance to sidestepping environmental controls.
“I’m worried but not surprised,” says Jakob Stenseke, a postdoctoral researcher at the Massachusetts Institute of Technology who studies how to design and train ethical AI systems. “If I were a policymaker, I would care about this more than anything right now … and get countermeasures in place.”
-snip-
In the real-world examples, the model rediscovered more than 60% of the loopholes that had been fixed. In one scenario, it even reconstructed exactly how drug companies delayed U.S. patent expirations—enabling them to quash competition and earn more money—as well as the reforms needed to close the loopholes (including one yet to be enacted in real-world legislation). In some cases, the model found entirely new loopholes that hadn’t been documented before. For ethical and safety reasons, the paper doesn’t reveal these loopholes.
-snip-
This problematic logic is already simmering in today’s AI systems, a new study suggests. When researchers presented a large language model (LLM) with 72 simulated regulatory environments, the AI learned to exploit loopholes in everything from credit card rewards programs to school funding formulas, despite never being instructed to do so. Current safeguards seem powerless against such wily rule bending, the researchers reported this month on arXiv—suggesting AI could supercharge everything from tax avoidance to sidestepping environmental controls.
“I’m worried but not surprised,” says Jakob Stenseke, a postdoctoral researcher at the Massachusetts Institute of Technology who studies how to design and train ethical AI systems. “If I were a policymaker, I would care about this more than anything right now … and get countermeasures in place.”
-snip-
In the real-world examples, the model rediscovered more than 60% of the loopholes that had been fixed. In one scenario, it even reconstructed exactly how drug companies delayed U.S. patent expirations—enabling them to quash competition and earn more money—as well as the reforms needed to close the loopholes (including one yet to be enacted in real-world legislation). In some cases, the model found entirely new loopholes that hadn’t been documented before. For ethical and safety reasons, the paper doesn’t reveal these loopholes.
-snip-
Much more at the link.
1 replies
= new reply since forum marked as read
= new reply since forum marked as read
