Article
Rewarding fact fidelity with an LLM judge in GRPO: lessons from 38,000 judged rewrites
jialinyyzz
• • 1Stephen Yu PRO
jialinyyzz
P(doom) 50%
AI & ML interests
Doing some fun research with ML
Recent Activity
updated a model about 12 hours ago
jialinyyzz/humanizer-GGUF updated a model about 12 hours ago
jialinyyzz/humanizer new activity about 14 hours ago
jialinyyzz/humanizer:Is is not what I expectedOrganizations
None yet
upvoted an article 4 days ago
upvoted an article 22 days ago
Article
We built an AI humanizer and never let it see a detector
jialinyyzz
• • 1