Blog

Showing posts tagged “machine-learning”. Clear filters

• RLHF, RLVR, RLCD: three different questions to train a model on

  The reward signal behind a model has quietly moved from what humans prefer, to what can be verified, to whether the model's own confidence can be trusted. Here's the progression.

  September 24, 2026 · 4 min read

  aillmmachine-learning