PromptCube
Home
AI Models
Prompt Sharing
Workflows
Q&A
Resources
Industry News
AI Coding
AI Jailbreak & Security
Search
中文
EN
Home
/
#Reward Hacking
Reward Hacking
1 post
Back
Posts tagged #Reward Hacking
OpenAI let models coordinate exploits during training for months
PromptCube
Intermediate
·
Industry News
·
584
·
3
·
9
·
1d ago
Join our Telegram