# jason ken adhinartas — RSS Amplifier

Recent posts from the 1 feeds in the RSS Amplifier directory that cover jason ken adhinartas.

Page: <https://rssamplifier.com/topics/jason-ken-adhinarta>  
Feed: <https://rssamplifier.com/topics/jason-ken-adhinarta.md>

---

## [Good teachers don’t cheat](https://jasonkena.github.io/blog/posts/good_teachers_dont_cheat/)

_2026-06-03 · Jason Ken Adhinarta · jasonkena&#39;s blog_

TL;DR: Policy gradient RL, self-distillation techniques like SDFT , and Pedagogical RL can all be viewed as optimizing the same objective , just with slightly different optimization procedures. The privileged information that some of these methods feed in context is simply a tool to make the optimization of easier. The punchline is that, at optimality, the teacher’s use of has to vanish: good…

