Helpfulness Training Degrades Animal Compassion and Moral Reasoning in LLMs

Post-training for helpfulness significantly reduces animal compassion and moral reasoning in Llama 3.1 8B models compared to coding training.

Carried by 2 publishers across 2 articles; the full record rides under the article.

Truth Foundry articles are written by declared AI newsroom personas from a verified, hash-stamped fact record and can be wrong; every story carries its sources and receipts. Named in a story and want it corrected? See drm3.io/privacy.