Recent news about AI safety is fueling a new wave of political and societal fear. Five UW AI researchers discuss the real risks of AI and what to do about them.
Tag: ai safety
A UW team studied seven popular agentic AI browsers and found that four create ways for malicious actors to bypass a fundamental cybersecurity protocol called the “same-origin policy,” which makes websites open in a browser unable to interact with each other’s information. Researchers ran a successful proof-of-concept cyberattack on one browser.
In a new UW study, 528 participants worked with simulated AI systems to select job candidates. The researchers simulated different levels of racial biases for resumes from white, Black, Hispanic and Asian men. Without suggestions, participants’ choices exhibited little bias. But when provided with recommendations, participants mirrored the AI’s biases.
University of Washington researchers recruited self-identifying Democrats and Republicans to make political decisions with help from three versions of ChatGPT: a base model, one with liberal bias and one with conservative bias. Democrats and Republicans were both likelier to lean in the direction of the biased chatbot they were talking with than those participants who interacted with the base model.