Surprising gender biases in GPT

Original Article ↗ Hacker News Discussion ↗

Researchers claim GPT-4 shows asymmetric gender bias, more readily endorsing women in traditionally male roles than men in caregiving or “feminine” ones, which many commenters see as unsurprising given both internet training data and Silicon Valley–style alignment. Some argue the study mostly rediscovers biases intentionally added during reinforcement learning, while others question its methodology, such as childlike prose and spelling errors in prompts. The thread broadens into a debate over whether such model behavior reflects real-world gender norms, is driven by political agendas in AI safety, and how it intersects with wider disputes about feminism, equality, and social engineering.

Paper design and quality

  • Several commenters criticize the prompts’ spelling/grammar, initially assuming sloppiness.
  • Others note the paper explicitly aimed to mimic elementary-school writing with typical errors and that authors are ESL, which some see as reasonable.
  • A few argue that “playing with ChatGPT” is too thin to be a serious paper; they expect broader cross-linguistic, cross-cultural analysis of gender in language models.

Source of GPT’s gender bias

  • One camp sees bias as a direct artifact of training data: scrape the internet, get its sexism and norms, then models echo them.
  • Another camp argues RLHF and alignment are the main cause, deliberately pushing models toward “pro-female/anti-male” or “woke” norms, citing examples like image models refusing to show certain demographics.
  • Some note that alignment seems to work only in obvious, explicit cases; subtle biases leak through.

Using GPT to infer real-world attitudes

  • Some say the paper is only about GPT-4’s behavior, not society.
  • Others point out the authors interpret biases as reflecting human text corpora and thus underlying social attitudes.
  • A few find this move questionable: GPT is a tuned commercial product, not a neutral survey instrument.

Societal gender norms and feminism (large tangent)

  • Many tie GPT’s asymmetries to real-world patterns: society warmly supports women entering “masculine” roles but is less accepting of men in caregiving or “feminine” roles.
  • Multiple comments discuss higher female college enrollment, targeted programs for women, and perceived neglect of boys/men.
  • Debates flare over feminism’s goals (equality vs “overcorrection”), equal opportunity vs equal outcomes, and whether modern policies mainly serve economic growth (expanding workforce) rather than families.
  • Examples raised include parental leave asymmetries, domestic labor imbalance, and lingering patriarchal norms vs emerging “anti-male” sentiment.

Language, bias, and technical notes

  • Some explore how pronoun choice (“he”/“she”/“they”) interacts with stereotypes and information efficiency.
  • Others discuss whether LLMs can be used as instruments to measure societal bias, or whether alignment and corporate filters distort that signal.
  • A few suggest directly inspecting base models’ token probabilities (e.g., for “he” vs “she”) as a cleaner way to study bias.