Modaic

23 posts

Modaic

@modaicdev

signatures are eating the world...

San Francisco, CA Joined Eylül 2025

14 Following112 Followers

Modaic@modaicdev·27 Şub

Open source btw! github.com/modaic-ai/moda…

Tyrin@ty_todd1

We put together a guide for @DSPyOSS using @mintlify to help beginners quickly learn the patterns for using DSPy in production. docs.modaic.dev/dspy_guide/get… Here are some of the highlights that'll help you get past the DSPy learning curve faster 🧵

English

949

Modaic retweeted

Farouk@FaroukAdeleke3·13 Oca

follow ML best practices in your optimization runs with the modaic sdk modaic.dev/blog/modaic-br…

English

412

Modaic retweeted

Ankur Gupta@getpy·7 Oca

Next episode in the DSPy Series will be with two young entrepreneurs @FaroukAdeleke3 and @ty_todd1 building @modaicdev which makes distributing your DSPy code easy. Subscribe @Informationshelf" target="_blank" rel="nofollow noopener">youtube.com/@Informationsh… to get the updates

English

3.3K

Modaic@modaicdev·25 Ara

Farouk@FaroukAdeleke3

Environments??

ZXX

205

Modaic retweeted

Farouk@FaroukAdeleke3·17 Ara

Holistic Benchmarking with dspy-helm from Asad Aali on @modaicdev ! ☺️ Paper: arxiv.org/pdf/2511.20836 Github: github.com/StanfordMIMI/d… Modaic: modaic.dev/asadaali

English

1.4K

Modaic retweeted

Farouk@FaroukAdeleke3·9 Ara

Inspired by the DSPy Codex, I built a @DSPyOSS scaffold for Claude Code on @modaicdev ! It shares full feature parity with Claude Agent SDK, including MCP servers, tool use, hooks, etc. but with a DSPy signature interface. Links below. x.com/AlexGDimakis/s…

Alex Dimakis@AlexGDimakis

Agent scaffolds are as important as models.

English

3.5K

Modaic@modaicdev·4 Ara

@eshorten300 @weaviate_io @awscloud @ContextualAI @ChonkieAI @p0 @Google @twelve_labs @llama_index We 💚 Weaviate

English

Modaic retweeted

Erika Shorten@eshorten300·4 Ara

December is the month for giving So here are 9 new Recipes demoing how to use @weaviate_io and @awscloud, @ContextualAI, @ChonkieAI, @p0, @Google, @modaicdev, @twelve_labs, and @llama_index 🧑‍🍳

English

109

12.7K

Modaic retweeted

Erika Shorten@eshorten300·4 Ara

Modaic and Weaviate 1. Modaic and Weaviate: Load the `CrossEncoderRanker` program from the Modaic Hub, as well as `PromptToSignature` (github.com/weaviate/recip…)

English

492

Modaic retweeted

Farouk@FaroukAdeleke3·3 Ara

About a year ago, @plasticlabs achieved SOTA with DSPy on the OpenToM benchmark. The benchmark tests models’ ability to track and reason about the beliefs, perceptions, intentions, and psychological states of simulated characters (social cognition). @vintrotweets experiments are now packaged and available on @modaicdev with the ability to run one of his optimized programs with your own variables and under your own evaluations. Links below.

English

1.7K

Farouk@FaroukAdeleke3·2 Ara

hmmm maybe like a package registry for DSPy programs…wonder if someone’s working on this hmmm

spacy@dosco

ai is an abstraction like everything in the computing stack, dspy is an abstraction one level up, we all need to think about what’s next

English

487

Modaic@modaicdev·2 Ara

@FaroukAdeleke3 hmmm 👀

Modaic retweeted

Farouk@FaroukAdeleke3·1 Ara

Most leaderboards use one fixed zero-shot prompt across all models. Problem: Different LMs have different “prompt ceilings.” When you give them all the same prompt, it becomes less about benchmarking models and more about benchmarking how that model performs on a fixed prompt. Solution: Stanford shows that adding structured prompting (especially zero-shot CoT via @DSPyOSS) lifts performance by ~4 points on average and can even flip model rankings on tasks like MMLU-Pro, GSM8K, and MedCalc.

English

575

Modaic retweeted

Farouk@FaroukAdeleke3·1 Ara

Extremely underrated paper out of Stanford, including one of the creators of MEDVal! Benchmarking the ceiling of LM's as systems (optimized prompting strategy + LM) instead of generalizing the same prompt over competing LM's proves to be a more holistic evaluation of their capabilities. arxiv.org/pdf/2511.20836

English

123

Modaic@modaicdev·18 Kas

game changer.

Tyrin@ty_todd1

I just created IntelliSense for @DSPyOSS. It's a VSCode extension that looks at your Signatures and gives you type hints for modules and Predictions. Download for VSCode #review-details" target="_blank" rel="nofollow noopener">marketplace.visualstudio.com/items?itemName… To download for cursor paste this link in your browser. cursor:extension/modaic.dspy-intellisense

English

Modaic@modaicdev·22 Eki

@MaximeRivest *sigh* Signatures

English

Maxime Rivest 🧙‍♂️🦙🐧@MaximeRivest·22 Eki

If DSPy were either Signatures or Prompt Optimization, but not both, which would you choose? If it were only Signatures, you’d have to type your whole prompt yourself in the description fields and docstrings. If it were only Prompt Optimization, you’d have to use an OpenAI or Instructor-type syntax for defining your initial prompt and structured outputs, and use string interpolation to insert your input fields.

English

2.8K

Modaic@modaicdev·21 Eki

Hot take: retrofitting RL into your agent is like taping a jet engine onto a bicycle. An RL-native agent development kit changes the entire build process-cleaner code, faster iteration, agents that are actually self-improving. The difference? Night and day.

English

297

Modaic retweeted

Farouk@FaroukAdeleke3·18 Eki

new blog! - software finally eats labor - ai applications as an operating system - we’re in a fuzzy state in ai engineering - necessary abstractions drive innovation - why an open source ecosystem needs to exist at the right abstractions modaic.dev/blog/prompts-a…

English

849

Modaic@modaicdev·17 Eki

@CShorten30 doing god’s work.

Connor Shorten@CShorten30

Open-sourcing retrieve-dspy! 💻🚀 While developing Search Mode for Weaviate's Query Agent, we dove into the literature. It was amazing, and overwhelming, to see how many different takes on Compound Retrieval Systems there are! 📚 From perspectives on Reranking, such as to reason, or not to reason with Cross Encoders, Sliding Window Listwise Rankers, Top-Down Partitioning, Pairwise Ranking Policies, .... to Query Expansion, such as HyDE, LameR, ThinkQE, ..., Query Decomposition, Multi-Hop Retrieval, Adaptive Retrieval, and more... There are endless design decisions for building Compound Retrieval Systems!! 🛠️ Inspired by the work on LangProbe from @ShangyinT et al., retrieve-dspy is a collection of DSPy programs from the IR literature. I hope this work will help us better compare these systems such as HyDE vs. ThinkQE, or Cross Encoders vs. Sliding Window Listwise Reranking, and understand the impact of DSPy's optimizers! 🧩🔥 The first step of many, repo linked below!

English