roampal's submissions

1.		1% vs. 67%: What happened when we stopped trusting embeddings alone (roampal.ai)
		16 points by roampal 48 days ago \| past \| 7 comments
2.		RAG accuracy jumped from 10% to 60% when I added outcome scoring (roampal.ai)
		11 points by roampal 64 days ago \| past \| 7 comments
3.		Show HN: I made Claude Code learn from its mistakes (github.com/roampal-ai)
		4 points by roampal 70 days ago \| past
4.		Show HN: Roampal – a local memory layer that learns from outcomes (github.com/roampal-ai)
		1 point by roampal 84 days ago \| past \| 4 comments