https://hackerpaper.kaipfister.de/p/2404.14544/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMThttps://news.ycombinator.com/item?id=42347675urn:hackerpapers:mention:2404.14544:42347675Sat, 07 Dec 2024 06:21:18 GMT<p>The main idea behind DSPy is that you can’t modify the weights, but you can perhaps modify the prompts. DSPy’s original primary customer was multi-llm-agent systems where you have a chain / graph of LLM calls (perhaps mostly or all to OpenAI GPT) and you have some metric (perhaps vague) that you want to increase. While the idea may seem a bit weird, there have been various success stories, such as a UoT team winning medical-notes-oriented competition using DSPy https://arxiv.org/html/2404.14544v1</p><p><a href="https://hackerpaper.kaipfister.de/p/2404.14544/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.CL