LessWrong6 min read
Self-reward can elicit diverse model personas
Epistemic status: This is mostly a toy project rather than a thorough scientific investigation. Most design choices are not ablated. We list some caveats at the end of the post.We let Qwen3.5-2B choose its own reward during GRPO on introspection-adjacent prompts, and this ends up eliciting quite…
By Ziqian ZhongLessWrong

Read the full story
Originally published by LessWrong on Oct 24, 2026.
Comments
Sign in to join the discussion.