TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Betting on DSPy for Systems of LLMs

83 点作者 wavelander9 个月前

6 条评论

NeutralCrane9 个月前
The more I’ve looked at DSPy, the less impressed I am. The design of the project is very confusing with non-sensical, convoluted abstractions. And for all the discussion surrounding it, I’ve yet to see someone actually <i>using</i> for something other than a toy example. I’m not sure I’ve even seen someone prove it can do what it claims to in terms of prompt optimization.<p>It reminds me very much of Langchain in that it feels like a rushed, unnecessary set of abstractions that add more friction than actual benefit, and ultimately boils down to an attempt to stake a claim as a major framework in the still very young stages of LLMs, as opposed to solving an actual problem.
评论 #41218357 未加载
评论 #41216615 未加载
评论 #41216015 未加载
评论 #41214243 未加载
评论 #41217298 未加载
okigan9 个月前
Could we have a concise and specific explanation how DSPy works?<p>All I&#x27;ve seen are vague definitions of new terms (ex. signatures) and &quot;trust me this very powerful and will optimize it all for you&quot;.<p>Also, what would a good way to reason between DSPy and TextGrad?
评论 #41215977 未加载
评论 #41215909 未加载
评论 #41218660 未加载
评论 #41316156 未加载
thatsadude9 个月前
I had a few problems with DSPy:<p>* Multi-hop reasoning rarely works with real data in my case. * Impossible to define advanced metrics over the whole dataset. * No async support
gunalx9 个月前
Not to say anything about dspy, but I really liked the take on hvat we should use llms for.<p>We need to stop doing useless reasoning stuff, and find acttual fitting problems for the llms to solve.<p>Current llms are not your db manager(if they could be you don&#x27;t have a db size in the real world). They are not a developer. We have people for that.<p>Llms prove to be decent creative tools, classificators, and qna answer generators.
评论 #41221174 未加载
fsndz9 个月前
I tried it recently and it is kinda fun: <a href="https:&#x2F;&#x2F;www.lycee.ai&#x2F;courses&#x2F;a5b7d115-c794-410d-92f2-15d8f2932130&#x2F;chapters&#x2F;bc227f31-3c8b-425b-99dd-c5e597ac943e" rel="nofollow">https:&#x2F;&#x2F;www.lycee.ai&#x2F;courses&#x2F;a5b7d115-c794-410d-92f2-15d8f29...</a>
revskill9 个月前
Whenever i see &quot;ChainOfThought&quot; for AI, it&#x27;s an annoying and misleading term. Machine never never thinks at all.