Article
Rewarding fact fidelity with an LLM judge in GRPO: lessons from 38,000 judged rewrites
jialinyyzz
• • 2Stephen Yu PRO
jialinyyzz
P(doom) 50%
AI & ML interests
Doing some fun research with ML
Recent Activity
liked a model about 12 hours ago
jialinyyzz/humanizer-GGUF new activity about 14 hours ago
jialinyyzz/humanizer:Installation Video and Testing - Step by Step liked a dataset about 14 hours ago
jialinyyzz/humanizer-dataOrganizations
None yet
published an article 5 days ago
published an article 23 days ago
Article
We built an AI humanizer and never let it see a detector
jialinyyzz
• • 1