#reasoning

2 pages search “reasoning” ↳ all tags

Wiki 2

  • Olmo 3 AI2's Olmo 3 report (Dec 2025), fully open 7B/32B Base, Think, Instruct and RL-Zero models with every stage's data, code and checkpoints released
  • Thinking-Mode Rule Erosion Reasoning modes degrade rule-following — when models "think," they evaluate whether contextual rules are load-bearing and skip the ones they decide are arbitrary