Unverified60% confidenceFactExact time
WorkBuddy's experience optimization program is enabled by default; when enabled, conversation data is submitted to the official team for model optimization and training.
2
Sources
60%
Confidence
Medium-term (~90 days)
Relevance
9/22/2026
First Seen
Valid until: 12/21/2026
Sources
Related Entities
Related Claims
UnverifiedWorkBuddy's "Experience Optimization Program" option is enabled by default, allowing the company to use user data to train models; turning this option off generally does not affect core functionality.77% similarUnverified一个典型的对话AI模型训练需经历四个阶段：预训练、有监督微调（SFT）、奖励模型训练和近端策略优化（PPO）76% similarUnverified针对代码任务专项强化训练的模型在系统操作场景中表现显著优于通用对话模型75% similarUnverifiedThe official version simplifies the full eight-stage post-training process into five easy-to-follow steps: define target behavior, generate synthetic dialogues at scale, review and split data, LoRA fine-tuning, and deployment and evaluation.72% similarUnverifiedHarden uses a dedicated post-trained model capable of understanding the user's original request and current session context72% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/941546API
curl https://kongchang.com/api/v1/knowledge/claims/941546MCP
get_claim(id=941546)