Ruibo Liu
Senior Research Scientist @Google DeepMind

llm

2025 Thoughts
✦ September

Learnings from Cursor Tab

Some notes on Cursor's "Tab RL" blog: To use policy gradient methods to improve Tab, we
2025 Thoughts
✦ September

Confidence != Wisdom

The single most dangerous design flaw in today's language models isn't that they hallucinate; it'
2025 Thoughts
✦ September

LLM's Data

We obsess over model architecture and FLOPS, but the most important component of any new language model is the one

Explore more topics

rl cursor rewards confidence model_behavior hallucination data compensation