While AI's picture

While AI

whileai
·

AI & ML interests

Agents make mistakes. Those mistakes are the most valuable training data there is. Only while ai turns them into a dataset, post-trains an open model on it with SFT and RL, and proves the agent stopped repeating them on a held-out test.

Recent Activity

updated a model about 2 hours ago
whileai/text-to-sql-shop-qwen3.5-9b-r3-step50-vllm
published a model about 2 hours ago
whileai/text-to-sql-shop-qwen3.5-9b-r3-step50-vllm
updated a dataset about 7 hours ago
while-ai/brand
View all activity

Organizations

While AI's profile picture