Uploaded April 2025 | Updated September 2026, 3 days ago
Tilde
pretalx.northbaypython.org/nbpy-2025/talk/ZEFTCV
Large language models are only as good as the data we feed into them. Unfortunately, we haven't quite dismantled racism, sexism, and all the other -isms just yet. Generative AI isn't going away, so let's apply a harm reduction lens. Given the imperfect tools that we have, how can we write LLM prompts that are less likely to reflect our own biases? In this session, we'll will review 5 current research papers straddling the intersection of prompt engineering and social science. We'll also walk through an interactive live demo in Python, showing how to apply this research to real world problems. You'll leave with some ideas about how you, as users and builders of generative AI applications, can iterate towards a more equitable world.
Sun Apr 27 16:20:00 2025 at Reis River Ranch
Produced by NDV: youtube.com/channel/UCQ7dFBzZGlBvtU2hCecsBBg?sub_confirmation=1
Tilde
pretalx.northbaypython.org/nbpy-2025/talk/ZEFTCV
Large language models are only as good as the data we feed into them. Unfortunately, we haven't quite dismantled racism, sexism, and all the other -isms just yet. Generative AI isn't going away, so let's apply a harm reduction lens. Given the imperfect tools that we have, how can we write LLM prompts that are less likely to reflect our own biases? In this session, we'll will review 5 current research papers straddling the intersection of prompt engineering and social science. We'll also walk through an interactive live demo in Python, showing how to apply this research to real world problems. You'll leave with some ideas about how you, as users and builders of generative AI applications, can iterate towards a more equitable world.
Sun Apr 27 16:20:00 2025 at Reis River Ranch
Produced by NDV: youtube.com/channel/UCQ7dFBzZGlBvtU2hCecsBBg?sub_confirmation=1
