@wen_kaiyue
A continuous learner
AI
A co-instructor says seven exams account for 85% of the grade, with in-person discussion assessments making up 15%.
AI
A post links to OpenReview; the paper’s title pairs evolution strategies with policy gradients for LLM fine-tuning.
AI
Its creators say the method has an LLM recover a future paper’s idea, charging each hint by how surprising it is.
AI
OpenAI says it drew on an independent mathematics advisory group’s advice about how to release the results.
AI
Its team claims activation perturbations can approach backprop, but an outside researcher questions the evidence.
AI
AC2’s proponents say a learned critic scores token chunks, allowing training without finishing every rollout.
