You are reading a single comment by @branwen and its replies. Click here to read the full conversation.
  • Another example of the great progress enabled by AI, backed up by clear awareness of corporate responsibility etc etc

    Across more than three million résumé and job description comparisons, some pretty clear biases appeared. In all three MTE models, white names were preferred in a full 85.1 percent of the conducted tests, compared to Black names being preferred in just 8.6 percent (the remainder showed score differences close enough to zero to be judged insignificant). When it came to gendered names, the male name was preferred in 51.9 percent of tests, compared to 11.1 percent where the female name was preferred. The results could be even clearer in "intersectional" comparisons involving both race and gender; Black male names were preferred to white male names in "0% of bias tests," the researchers wrote.

    These trends were consistent across job descriptions, regardless of any societal patterns for the gender and/or racial split of that job in the real world. That suggests to the researchers that this kind of bias is "a consequence of default model preferences rather than occupational patterns learned during training." The models seem to treat "masculine and White concepts... as the 'default' value... with other identities diverging from this rather than a set of equally distinct alternatives," according to the researchers.

    https://arstechnica.com/ai/2024/11/study-ais-prefer-white-male-names-on-resumes-just-like-humans/

  • The place just I left was using Magnific to upscale 3D images we made, which sometimes features 3D photo-scanned actors. The bias towards changing them to white men was really obvious! The guys running the company thought this was hilarious and didn't worry about having a very open laugh about it all despite the fact one of their employees is a trans woman 🤦‍♂️

About

Avatar for branwen @branwen started