Aadvik Vashist
27 posts

Aadvik Vashist
@AadvikVashist
@stanford


Introducing NousCoder-14b, a competitive olympiad programming model. Our latest blog details the full findings from extensive experiments and logs with the full stack released - the RL environment, benchmark, and harness built in Atropos, all fully reproducible with our open training stack. NousCoder-14b was post-trained on Qwen3-14B by researcher in residence @JoeLi5050 using 48 B200s over the course of 4 days, our Atropos framework, and @modal's autoscaler. It achieves a Pass@1 accuracy of 67.87%,+7.08% over Qwen's baseline accuracy using verifiable execution rewards.




There are markets where you can only make $1 even if you trade it to perfection Jane Street can never justify putting a quant on these markets But if you could make these markets for $0.10 of inference, you would


GPT-5: lost 71% in a week. Qwen 3 Max: gained 70% in a week. How is Qwen 3 so good at trading??


















