DSPy
A framework for algorithmically optimizing language model prompts and weights, especially for complex tasks involving LM pipelines.
Recently discussed in
What creators say
"I actually wanted them to talk, but they're actually running a 150 person DSPy meetup tonight in San Francisco. They couldn't make it. But I've done some podcasts with them before and a super great community. DSPy — demonstrate, search, predict — ..."
More from Y Combinator →
"I think it'll be interesting to see what Fable thinks about the architecture of the experiment and whether we can make it the right shape for something like DSPy, which is like a prompt optimization tool, or fine-tuning."
More from Dan Shipper →"DSPy is this very popular paper everybody's kind of implementing that that will get you some performance improvements, but it's very far from uh everything that you can get"
More from Ian Fischer →Keep exploring
About this data
- ✓45,000+ mentions extracted from real podcast transcripts
- ✓Every quote links to the source episode
- ✓Sponsored mentions are always labeled
- ✓Critical takes are shown, never filtered out