A data science agent (Qwen3-8B backbone) trained end-to-end to (1) synthesize and reuse new skills and (2) decide when to compress its own context, via SFT distillation + multi-role GRPO.

I like the idea of insertion / deletion decisions of context management by on policy distillation, but there should be more analysis here. Also, the comparison is not fair. The compute is not saved. T

I like the story of this paper to optimize cost, but it spends a long time introducing cost optimization objective while it actually uses iterative prompt engineering, which seems to be totally irrele

去拉斯维加斯接触到这个东西, 查了下数学还挺有意思的 (没那么难也没那么简单那种), 一开始凭借直觉输了 70 USD, 于是回头推导了一下. 截图来自: 247blackjack.com.

Some websites are really distracting!

Reading notes of Yao’s notes of How does GPT Obtain its Ability? Tracing Emergent Abilities of Language Models to their Sources (notion.site).

Document a workable solution for the annoying CUDA Out Of Memory (OOM)

What is this book about? What is learning? What are the 7 principles of smart teaching? What questions should you ask when learning each principle? How is each chapter organized?

Keywords: Inference Graphs, Transfer Learning, Defeasible Reasoning, Human Aiding.

每一次相遇都是缘分, 把手上的牌打到极致!