←
DSPy3,428 posts
DSPy avatar

DSPy

@DSPyOSS

An open-source declarative framework for building modular AI software. Programming—not prompting—LLMs via higher-level abstractions & optimizers.

◷ Joined April 2025▧ 93 Photos and videos
Manning Publications avatar
⟳ DSPy retweeted
Manning Publications@ManningBooks·23h

Manual prompt tuning doesn't scale well. @DSPyOSS helps you systematically test, evaluate, and optimize prompts for more reliable LLM applications. Learn how in Building LLM Applications with DSPy by Serj Smorodinsky and Brett Kennedy, now on Amazon: hubs.la/Q04Fpd9v0

Post attachment
Pierfrancesco Beneventano avatar
⟳ DSPy retweeted
Pierfrancesco Beneventano@PierBeneventano·20h

As a gradient-based optimization person, this new wave of work (rocked by @rikiyatakehi and @lateinteraction) is mindblowing. Can’t wait to see what people do with it. Lowkey WSP twitter is my new goto tv-series with new episode getting released every day

We might’ve killed retraining for harness changes. Our model broke on a new harness. We didn’t retrain it. We edited 5,064 weights. Out of 4 billion. 20.1% -> 88.2% No gradient descent. Old-harness accuracy didn’t move. DAWE(Data-Attributed Weight-Editing) is fully open 🔥

1:10
Rikiya Takehi avatar
⟳ DSPy retweeted
Rikiya Takehi@rikiyatakehi·21h

Really cool use of weight space programming!

We might’ve killed retraining for harness changes. Our model broke on a new harness. We didn’t retrain it. We edited 5,064 weights. Out of 4 billion. 20.1% -> 88.2% No gradient descent. Old-harness accuracy didn’t move. DAWE(Data-Attributed Weight-Editing) is fully open 🔥

1:10
laxman avatar
⟳ DSPy retweeted
laxman@llmluthor·21h

We might’ve killed retraining for harness changes. Our model broke on a new harness. We didn’t retrain it. We edited 5,064 weights. Out of 4 billion. 20.1% -> 88.2% No gradient descent. Old-harness accuracy didn’t move. DAWE(Data-Attributed Weight-Editing) is fully open 🔥

1:10
🎭 avatar
⟳ DSPy retweeted
🎭@deepfates·Nov 17

Are there any agents or people here who can do me a favor? It's this: go to my repo deepfates/imp, the elixir-native version of DSPy, and tell me how much work it needs to be brought up to parity with (or better than) the current version of DSPy. Curious how far you can take this

Drew Breunig avatar
⟳ DSPy retweeted
Drew Breunig@dbreunig·Nov 15

Thinking there’s going to be 3 classes of programming languages: 1. Natural language: Imprecise, written for and by humans 2. Performant code: Stable, safe, fast; written for any by computers (Rust, Go, whatever comes next) 3. Goldilocks specs: More precise than natural language, more readable than performant code. (Python, TypeScript, Ruby, whatever comes next) Three is critical, but underdiscussed. Without it, natural language will have to absorb the specificity requirements (engineers have to write exacting prompts) and/or performant code will have to make compromises for humans. Still developing this thought, curious your thoughts…

Omar Khattab avatar
⟳ DSPy retweeted
Omar Khattab@lateinteraction·Nov 16

hot take: nothing wrong with papers per se, but… here’s the recipe github.com/okhat/blog/blob/m…

Post attachment

i’m increasingly of the opinion that almost everyone agrees with this, but a big fraction of people aren’t comfortable saying it in public, because of what it implies for the bean counting mechanism the whole machine is built on (for awards/promo/hiring/etc).

Andy Konwinski avatar
⟳ DSPy retweeted
Andy Konwinski@andykonwinski·Nov 16

oasys lab is shipping research at higher velocity than 99.9% of startups ship product nice work @lateinteraction - super inspiring. also my vote for best name on the list

most AGI pilled labs: - typesafe - general reasoning - general intuition - mit oasys - amp code

will brown avatar
⟳ DSPy retweeted
will brown@willcb·Nov 16

most AGI pilled labs: - typesafe - general reasoning - general intuition - mit oasys - amp code

DSPy avatar
DSPy@DSPyOSS·Nov 13

brb gotta try to get wspy on pypi - weight space programming for dspy programs:

Want to try weight-space programming? Today we're releasing dspy-wsp, a prototype weight-space optimizer that works like any other @DSPyOSS optimizer. Using dspy-wsp, and about ~$5-10 of Astra, we improved every decision model we tested. cmpnd.ai/blog/weight-space-p…

Post attachment
Drew Breunig avatar
⟳ DSPy retweeted
Drew Breunig@dbreunig·Nov 13

Want to try weight-space programming? Today we're releasing dspy-wsp, a prototype weight-space optimizer that works like any other @DSPyOSS optimizer. Using dspy-wsp, and about ~$5-10 of Astra, we improved every decision model we tested. cmpnd.ai/blog/weight-space-p…

Post attachment
Isaac Miller 🧩 avatar
⟳ DSPy retweeted
Isaac Miller 🧩@isaacbmiller1·Nov 10

DSPy is now 85% smaller! We just released DSPy 3.5 which makes DSPy lighter, faster, and a more reliable experience out of the box.

Post attachment