i think i figured out the correct pipeline for RL 1 : forget RL and...

@casper_hansen_
Casper Hansen@casper_hansen_
11 views Oct 27, 2025 ~1 min read
Advertisement
1
i think i figured out the correct pipeline for RL

1 : forget RL and just do DSPy with GEPA. develop your agent loop and eval here. it's cheaper and faster.

2 : convert it to RL and compare to baseline.

3 : hopefully RL worked, otherwise revert to prompt optimizers
2
step 1 allows you to forget about GPUs and infrastructure. just hit your favorite inference provider.

it also lets you figure out what metrics work in an optimization flow. this makes it significantly cheaper to develop things from scratch.

it may not outperform RL in every scenario, but it has advantages that i cannot seem to get elsewhere
Actions
What You Can Do
  • Export as PDF or Markdown
  • Batch Export to Notion
  • Bookmark & Highlight
  • Screenshot Tweet
Create Free Account

Includes 7-day Premium trial

Advertisement