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.
More from Models
- Is More Reasoning Better? High Compute May Cause Repetitive Loops — CoVegGirl · 2026-08-12
- Alignment Degrades Capabilities? User Complains Anthropic's Models Are Getting Worse — cephaloform · 2026-08-12
- Anthropic's Computer Use tested: works in Chrome, lacks full desktop control — cedric_chee · 2026-08-12
- Rumor: SpaceXAI to Finalize $60B Cursor Acquisition and Launch Grok 4.6 on August 14 — koltregaskes · 2026-08-12
- Meta Drops 30B Local Open-Source Model as OpenAI Unveils Unrestricted Cybersecurity AI — Dapper-Tale-4021 · 2026-08-12
- Elon Musk: Grok 4.6 to Launch Later This Week After Early Bug Fixes — XFreeze · 2026-08-12