Anshul Gokul
CS & mathematics at Georgia Tech. Previously post-training research at DeepGrove.
We build games and simulations that help models
learn to solve problems they haven’t seen before.
Which experiences make a model more capable? We’re starting with interactive worlds, measuring what transfers to other tasks, and using those results to design better training environments.
CS & mathematics at Georgia Tech. Previously post-training research at DeepGrove.
CS at Georgia Tech. Previously quantitative trading systems at Optiver and Qube Research.