Show HN: Llama-8B Teaches Itself Baby Steps to Deep Research Using RL https://ift.tt/Z29yRzB

Show HN: Llama-8B Teaches Itself Baby Steps to Deep Research Using RL I've been tinkering with getting Llama-8B to bootstrap its own research skills through self-play. The model generates questions about documents, searches for answers, and then learns from its own successes/failures through RL (hacked up Unsloth's GRPO code). Started with just 23% accuracy on Apollo 13 mission report questions and hit 53% after less than an hour of training. Everything runs locally using open-source models. It's cool to see the model go from completely botching search queries to iteratively researching to get the right answer. https://ift.tt/12czdvT March 10, 2025 at 11:05PM

Komentar

Postingan populer dari blog ini

Twin Peaks for All: Survey Results

Launch HN: Riot (YC W20) – Phishing training for your team https://ift.tt/2QIueZL

Launch HN: Stacker (YC S20) – Create Apps from Airtable or Google Sheets https://ift.tt/3i3ZJso