Skip to content
X · @teortaxesTex · X / Twitter

Happy automated inference optimization day to all who celebrate

Happy automated inference optimization day to all who celebrateAsari AI: The most interesting part? Seeing our agents learn and improve from each run.While optimizing DeepSeek v4 Pro, the agents learned how to avoid a distributed deadlock.When they later hit a similar situation optimizing GLM 5.2, they generalized that