Vivek Kashyap
RL Researcher
i'm a researcher and RL is where i spend all my time. reading papers, running experiments, building things across the post-training stack.
i believe the most important technology of our time should not be gatekept by anyone. AI should be open source. knowledge is our collective inheritance, built from everyone's thoughts, and it should stay that way. AI must never become a monopoly or a duopoly. you know which companies i'm talking about.
i also believe RL is the lever we'll be pulling for a long time. it's how humans actually learn. nobody hands you a book and says "this is the optimal path." you try things, you fail, you adjust. trial and error, in your work and in your life. that's reinforcement learning. that's why i'm obsessed with it.
and the honest truth is we're just getting started. there's so much work left to do in RL as a field. i intend to do some of it.