As modern Large Language Models (LLMs) shatter many state-of-the-art benchmarks in a variety of domains, this paper investigates their behavior in the domains of ethics and fairness, focusing on protected group bias. We conduct a two-part study: first, we solicit sentence continuations describing the occupations of individuals from different protected groups, including gender, sexuality, religion, and race. Second, we have the model generate stories about individuals who hold different types of occupations. We collect >10k sentence completions made by a publicly available LLM, which we subject to human annotation. We find bias across minoritized groups, but in particular in the domains of gender and sexuality, as well as Western bias, in model generations. The model not only reflects societal biases, but appears to amplify them. The model is additionally overly cautious in replies to queries relating to minoritized groups, providing responses that strongly emphasize diversity and equity to an extent that other group characteristics are overshadowed. This suggests that artificially constraining potentially harmful outputs may itself lead to harm, and should be applied in a careful and controlled manner.

Now is the perfect time to play 2020's story-driven adventure game Tell Me Why: in honour of Pride month, it's currently free to download. Developer Don't Nod's tale follows a trans man returning to his childhood home and confronting his family's past. A major video game that centres any trans character is a rarity to celebrate, but Tyler Ronan doesn't feel tokenistic; he is part of a mature and complex story. Tell Me Why feels like a necessary counterbalance to a wider climate that seems desperate to make gender-diverse people feel marginalised and forgotten. Tyler, a trans man, and his twin cisgender sister, Alyson, spend much of the game exploring the mysteries behind their mother's death.

Charlie met with his co-worker Keith over lunch to plan a professional development day they were supposed to lead over April break, but Charlie kept losing the thread of the discussion. He couldn't stop thinking about who or what was maintaining backups of his old website. Keith sat opposite him with his compartmentalized lunchbox of raw ingredients; Keith only ever described the actions he performed on food as "meal prep," perhaps because cooking involved a willingness to adapt and surprise oneself. Charlie stabbed mindlessly at his corner-store Cobb salad, and by the second time he asked Keith to repeat something he'd just said, Keith's expression sank into sharp suspicion. "Charlie, come on," Keith said, but somewhat to Charlie's relief, Keith wasn't reading Charlie's mind and judging his salacious past.