DEDer_Einzige·Sep 25, 2024
At least some of it comes from "hype" too. The author of Dspy (the writer) (https://github.com/stanfordnlp/dspy) should know this, given that Dspy is nothing more than fancy prompts optimizing prompts to be fancier according to prompt chains described in papers (i.e. Chain of thought, Tree of thought, etc). Textgrad (https://github.com/zou-group/textgrad) is an even worse example of this, as it makes people think that it's not just a prompt optimizing another prompt
Dspy has 17k stars, meanwhile PyReft (https://github.com/stanfordnlp/pyreft) isn't even at 1200 yet and it has Christopher Manning (head of AI at stanford) working on it (see their paper: https://arxiv.org/abs/2404.03592). Sometimes what the world deems "impactful" in the short-medium term is wrong. Think long term. PyReft is likely the beginning of an explosion in demand for
Read the rest
ultra parameter efficient techniques, while Dspy will likely fade into obscurity over time.
I also know that the folks writing better samplers/optimizers for LLMs get almost no love/credit relative to the outsized impact they have on the field. A new sampler potentially improves EVERY LLM EVER! Folks like Clara Meister or the authors of the min_p paper preprint have had far larger impacts on the field than their citation counts might suggest, based on the fact that typiciality or min_p sampling is now considered generally superior to top_p/top_k (OpenAI, Anthropic, Gemini, et al still use top_p/top_k) and min_p/typicality are implemented by every open source LLM inference engine (i.e. huggingface, vllm, sglang, etc)