Xin Yan

@cakeyan9

Research Scientist @ ByteDance Seed | Prev. @UWaterloo @MITIBMLab @01AI_Yi @WHU_1893

cakeyan.github.io

Joined February 2022

733 Following

104 Followers

Replies Reposts Media

Xin Yan
@cakeyan9
Sep 23
grok 4.7 is quite good in cursor. super fast. better than my codex!
Xin Yan
@cakeyan9
Sep 17
this is open ai
Fuli Luo
@_LuoFuli
Sep 16
Nearly half a year of silence. We spent it studying one problem: how far RL can scale. MiMo-V2.6 is in the middle of its RL run right now. Three things we scaled: compute (~2B tokens per step, 1568 prompts × 16 rollouts, fully async), environments and harnesses (multi-task
Xin Yan
@cakeyan9
Sep 8
it’s awesome. so sad that I am not part of the game now. got me rethinking what really matters.
OpenAI
@OpenAI
Sep 8
We’re sharing a solution to the Navier-Stokes Millennium Prize Problem, one of the deepest problems at the frontier of mathematics. The proof was produced by a group of agents, using an OpenAI next-generation model significantly more capable than GPT-6 Astra. The problem
Xin Yan
@cakeyan9
Sep 8
true
Samuel Zhang
@samuelxzhang
Sep 8
facts
Xin Yan
@cakeyan9
Aug 21
This is exactly what I needed! I’ve already installed it in Cursor. RAP checks whether the agent actually follows my Cursor Rules. Like I want agents to use my custom Parquet writer instead of writing their own, since they always put the entire dataset into a single row group.
Yuntian Deng @ EMNLP
@yuntiandeng
Aug 20
Frustrated your coding agent keeps ignoring your rules? What if every rule could take on a life of its own? I built RulesAsPrograms which turns each rule into a function that checks agent's work. Instead of hoping agent follows rules, rules check agent github.com/programasweigh…
1

Xin Yan

Xin Yan’s posts