Igor Babuschkin(@ibab):The River API was tested in this blog post and outperformed Tinker on reinforcement learning runs with identical training code. We spent a lot of effort to get details like routing replay right so you get the best possible results with the API.

Igor Babuschkin

@ibab

CEO & Co-Founder @river_ai_inc. Previously @xAI, Research & Engineering

가입 February 2020

893 팔로잉 중 111.2K 팬

Igor Babuschkin@ibab

2026.08.17 19:33

The River API was tested in this blog post and outperformed Tinker on reinforcement learning runs with identical training code. We spent a lot of effort to get details like routing replay right so you get the best possible results with the API.

Ashwinee Panda@PandaAshwinee

2026.08.17 16:59

We can now RL large MoEs with 0 train-infer mismatch! And doing so can improve performance (pictured task: teach Qwen3.6-35B-A3B to play Wordle). Everything is open-source and we did a bunch of ablations. 🧵