User questions why OpenAI doesn't RL against specific 'slop' in model outputs

kalomaze · x · 2026-08-12

User kalomaze quotes a discussion about Triton fast path and PyTorch fallback, questioning why OpenAI doesn't aggressively RL against this specific variety of 'slop' (low-quality outputs). The comment highlights concerns about quality control in model training.

Original post →

More from Models

Models channel →