Skip to content
{
ken ashe
}
Building
Topics
Blog
Building
Topics
Blog
←
Blog
/
Tags
// tag
post-training
5 posts tagged
post-training
.
Post-training is now the behavior layer
Aug 3, 2026
Output Reset makes PPO smoother, not automatically better
Jul 21, 2026
Muon’s agent RL win is real, narrow, and stack-dependent
Jul 20, 2026
Reusing RL Gains Across Model Sizes: The Case for Direct-OPD
Jul 7, 2026
Post-training logprobs as a step-level critic for agents
Jun 25, 2026