Research
Models, training, and evaluation.
Post-training a small model to follow a live stream of typing and learn when to act or stay quiet.
An ultra long-horizon benchmark for coding agents doing engineering and research work.
Mentioned in: Opus 4.8, Fable/Mythos, GLM-5.2, Kimi K3, Modular, Thoughtful Lab, Prime IntellectReinforcement-learning work for the browser-use model as a research intern.
Research internship at Amazon AGI, Mentioned in: RL training recipeAn RL setup in which language models learn their own compact codebooks.
Mentioned in: Deep Learning with YacineHidden-information games for studying deceptive behavior learned from reward.
Cross-lingual alignment through encoder injection for low-resource languages.
With Cohere Labs