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.
Could we have a concise and specific explanation how DSPy works?<p>All I've seen are vague definitions of new terms (ex. signatures) and "trust me this very powerful and will optimize it all for you".<p>Also, what would a good way to reason between DSPy and TextGrad?
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
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'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.
I tried it recently and it is kinda fun: <a href="https://www.lycee.ai/courses/a5b7d115-c794-410d-92f2-15d8f2932130/chapters/bc227f31-3c8b-425b-99dd-c5e597ac943e" rel="nofollow">https://www.lycee.ai/courses/a5b7d115-c794-410d-92f2-15d8f29...</a>