How I topped the OpenAI Parameter Golf challenge, twice

How I built an agentic system Hive to top the OpenAI Parameter Golf challenge, twice.

1 min read   ·   May 25, 2026

2026   ·   hive   agents   rllm   ·   announcements

Training Any Agentic Program without Code Changes

1 min read   ·   December 10, 2025   ·   rLLM Blog

2025

Starling-7B: Increasing LLM Helpfulness & Harmlessness with RLAIF

13 min read   ·   November 28, 2023   ·   Starling Blog

2023

Rethinking the Role of PPO in RLHF – The Berkeley Artificial Intelligence Research Blog

The BAIR Blog

10 min read   ·   October 16, 2023   ·   P3O Blog

2023