OpenAI and Anthropic had a “mini-pause” in RL training, a user claims
A September 1 post says both companies briefly paused reinforcement learning training.
TLDR
A user claimed on September 1 that OpenAI and Anthropic had just had a “mini-pause” in reinforcement learning (RL) training.
Combined views
67
2 Sources, first seen 29d ago
65 reposts