link.springer.com web signal

Generating the language of AI harms: mapping guardrails using critical code studies - AI & SOCIETY

By Alexis Dufresne Published October 29, 2026 at 18:12 UTC

Summary

Jill Walker Rettberg @jilltxt.bsky.social: I'm reading a fascinating paper by @sarahciston.com that analyses training datasets used to create guardrails for LLMs to avoid toxic conten… →
Amy Hoy @amyhoy.bsky.social amplified

Jill Walker Rettberg @jilltxt.bsky.social

I'm reading a fascinating paper by @sarahciston.com that analyses training datasets used to create guardrails for LLMs to avoid toxic content. So many interesting examples, and a very productive method. link.springer.com…
View on Bluesky →

Originally reported by link.springer.com

Original headline: Generating the language of AI harms: mapping guardrails using critical code studies - AI & SOCIETY