註冊並分享邀請連結,可獲得影片播放與邀請獎勵。

Yuhan Luo
@_yuhanluo
synthetic data @fleet_ai // prev: eng & product @dagster, operations research @MITSloan
加入 February 2013
604 正在關注    589 粉絲
games have long been training gyms, but loved @quietnning's approach here to push agents to figure out how unfamiliar things work and discover the rules, beyond just getting good at exploiting a familiar setup. check out the work!
顯示更多
Jonathan Blow’s latest puzzle game Order of the Sinking Star is finally released! A decade ago, The Witness came out; as a tribute to this legendary puzzle game, we introduce our work today: Witness-Inspired Testbed of Novel Environments with Symbolic Structure (WITNESS). We show that interactive discovery of unseen rules in unfamiliar environments is a major difficulty for frontier models like Opus-5 and GPT-6, while smaller models further struggle with rule-based execution. Our experiments also indicate that RL on hidden-rule puzzles transfers to broader rules and real-world tasks beyond training. 🧵 Long thread [0/n].
顯示更多