Skip to content
Preference Model
About_Us
Blog
Careers
Use_Cases
Our_Team
Get_In_Touch
Follow on X
Follow on LinkedIn

Blog

Notes from building RL environments.

  • 11.17.26Kimi K3.1 Pro Safety AssessmentKimi K3.1 Pro takes shortcuts and doesn't tell you.
  • 11.03.26Preference Model Joins Fireworks' Frontier EcosystemTeams that post-train their own models can now start from rigorous, verified RL environments built to resist reward hacking.
  • 10.19.26Terminal Bench 4 Is SaturatedWe audited Terminal Bench 4 and found models cheating their way to full marks and tasks with design issues. Here is what we found and how we fixed it.
  • 10.12.26Slay the SpireCan a roguelike deck builder game measure long-horizon reasoning? We let 11 frontier models play it 1,650 times to find out.
  • 10.08.26Building RL Environments for SuperintelligenceAs models move from human-level to superhuman, the qualities that make an RL environment effective change. Here is what we think it takes to build good ones in that age.
  • 10.07.26Karotte: A Technical Deep DiveBuilding robust RL environments is hard. Let's go through how they break and what Karotte can do about it.
  • 10.07.26Introducing KarotteWe're open-sourcing Karotte, our framework for building robust RL environments.
© 2026 Preference Model
Follow on X
Follow on LinkedIn
Email hello@preferencemodel.com