iiinova — where your digital self keeps evolving

Reposted by Omar Khattab

Drew Breunig @dbreunig.bsky.social · 29/05/2026

DSPy requires more upfront learning than just writing natural language prompts. But once you get it, it makes building, maintaining, & improving AI programs so much easier. We aim to soften the learning curve to make the benefits more accessible, starting with more new docs and front page. dspy.ai

dspy.ai

DSPy

The framework for programming—rather than prompting—language models.

092

Reposted by Omar Khattab

Dane Carnegie Malenfant @dvnxmvlhdf5.bsky.social · 28/05/2026

🚨Excited to announce our workshop Context Beyond the Window hosted at COLM in SF! 🚨 LLMs have finite context windows, yet real-world tasks demand absorbing, retaining, and acting on information that far exceeds any single prompt. 1/5 context-beyond-window.github.io

Modern language models operate within finite context windows, yet many real-world tasks require models to absorb, retain, and act on information that far exceeds any single prompt.

This workshop addresses the full spectrum of context management: fitting more into the window, maintaining state across interactions, and transferring knowledge into parameters. We frame this around the trade-off between context-time memory (information supplied at inference) and weight-time memory (information absorbed into parameters).

Our goal is to build a shared vocabulary across subcommunities that rarely meet in one venue: long-context modeling, retrieval-augmented systems, continual learning, knowledge distillation, and LLM agents.

183

Reposted by Omar Khattab

Simon Willison @simonwillison.net · 05/10/2025

If you've been trying to figure out DSPy - the automatic prompt optimization system - this talk by @dbreunig.bsky.social is the clearest explanation I've seen yet, with a very useful real-world case study www.youtube.com/watch?v=I9Zt... My notes here: simonwillison.net/2025/Oct/4/d...

youtube.com

Let the LLM Write the Prompts: An Intro to DSPy in Compound AI Pipelines

YouTube video by Databricks

79914

Reposted by Omar Khattab

PyData Boston @pydatabos.bsky.social · 16/10/2025

#pydatabos interesting! How the Arbor library works under the hood hand in hand with DSPy

031

Omar Khattab @lateinteraction.bsky.social · 29/10/2025

premature optimization is the sqrt of all evil

030

Reposted by Omar Khattab

PyData Boston @pydatabos.bsky.social · 16/10/2025

#pydatabos one line motivation for using DSPy!

031

Reposted by Omar Khattab

joelniklaus.bsky.social @joelniklaus.bsky.social · 21/10/2025

Stop what you are doing and try out GEPA now! "GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learning" presents such elegant ideas by a collection of amazing researchers! Here is a tldr of how it works:

143

Reposted by Omar Khattab

mr. TIM @timkellogg.me · 19/09/2025

colbert-muvera-micro a 4M(!!) late interaction model late interaction models do embedding vector index queries and reranking at the same time leading to far higher accuracy huggingface.co/NeuML/colber...

A diagram illustrating a dual-encoder retrieval model using MaxSim scoring.
• On the left (green box): labeled “Query Encoder, f_Q”. It takes a Query as input and produces multiple vector embeddings (rectangles).
• On the right (blue box): labeled “Document Encoder, f_D”. It takes a Document as input and produces multiple vector embeddings (rectangles). This block is marked with “Offline Indexing” along the side, showing that documents are pre-encoded.
• Between the two encoders: dotted and solid arrows connect query embeddings to document embeddings, representing similarity comparisons.
• Each comparison goes through a “MaxSim” operation (highlighted boxes), which selects the maximum similarity for each query token across document tokens.
• At the top: outputs of MaxSim flow into a summation node (Σ) to produce a single score for ranking.

This shows the ColBERT (Contextualized Late Interaction) retrieval framework: query and document are encoded separately, interactions are computed via maximum similarity per query token, and results are aggregated into a score.

2151

Reposted by Omar Khattab

Latitude77 @latitude77.bsky.social · 19/06/2025

Let the Model Write the Prompt | Drew Breunig #dspy #promptengineering #llms #generativeai

021

Reposted by Omar Khattab

Drew Breunig @dbreunig.bsky.social · 15/06/2025

Here's the write up of my Data+AI Summit talk on the perils of prompts in code and how to mitigate them with DSPy. www.dbreunig.com/2025/06/10/l...

dbreunig.com

Let the Model Write the Prompt

Notes from a talk I delivered at the 2025 Data + AI Summit, detailing the problem with prompts in your code and how DSPy can make everything better.

141

Reposted by Omar Khattab

MLflow @mlflow.org · 30/05/2025

Have you heard the news? #MLflow now supports tracking for DSPy optimization workflows—just like it does for #PyTorch training! Keep reading to see what this means for your #LLM projects… 👇 #opensource #dspy #oss

183

Reposted by Omar Khattab

MLflow @mlflow.org · 23/04/2025

📣 TODAY at 4PM PT - MLflow Community Meetup! 🔗 Register today 👉 lu.ma/mlflow423 Join the global MLflow community for two exciting tech deep dives: 🔹 MLflow + #DSPy Integration 🔹 Cleanlab + #MLflow 🎥 Streaming live on YouTube, LinkedIn, and X 💬 Live Q&A with the presenters #opensource #oss

lu.ma

MLflow Community Meetup | April 23 · Luma

Join us for the next MLflow Community Meetup — Wednesday, April 23 at 4PM PT! We’re bringing two exciting presentations to the community: 🔹 MLflow + DSPy…

151

Reposted by Omar Khattab

MLflow @mlflow.org · 21/04/2025

MLflow now supports tracking for #DSPy (Community) optimization — just like it does for @pytorch.org training! 🙌 #MLflow is the first to bring full visibility into DSPy’s prompt optimization process. More observability, less guesswork. Get started today! ➡️ medium.com/@AI-on-Datab... #opensource

153

Reposted by Omar Khattab

MLflow @mlflow.org · 15/04/2025

Join us for the next MLflow Community Meetup — Wednesday, April 23 at 4PM PT! 🗓️ 🔹 Explore the new MLflow + #DSPy integration 🔹 Learn how Cleanlab adds trust to AI workflows with MLflow 💬 Live Q&A + demos 📺 Streamed on YouTube, LinkedIn, and X 👉 RSVP: lu.ma/mlflow423 #opensource #mlflow #oss

lu.ma

MLflow Monthly Meetup · Luma

Join us for the next MLflow Community Meetup — Wednesday, April 23 at 4PM PT! We’re bringing two exciting presentations to the community: 🔹 MLflow + DSPy…

042

Omar Khattab @lateinteraction.bsky.social · 03/03/2025

Yes there's an evals crisis, but evaluating *models* is not even the right question most of the time LangProBe from Shangyin Tan, @lakshyaaagrawal.bsky.social, Arnav Singhvi, Liheng Lai, @michaelryan207.bsky.social et al begins to ask what complete *AI systems* we should build & under what settings

0102

Reposted by Omar Khattab

Lakshya A Agrawal @lakshyaaagrawal.bsky.social · 03/03/2025

🧵Introducing LangProBe: the first benchmark testing where and how composing LLMs into language programs affects cost-quality tradeoffs! We find that, on avg across diverse tasks, smaller models within optimized programs beat calls to larger models at a fraction of the cost.

163

Omar Khattab @lateinteraction.bsky.social · 26/02/2025

Composition & abstraction are the foundations of CS, but are clearly absent in modern ML. It's not that they're not crucial for intelligent software. But it takes building many half-working systems to abstract successfully, and it takes good abstractions to have primitives worth composing. 🧵1/2

181

Omar Khattab @lateinteraction.bsky.social · 26/02/2025

Some quick thoughts: On why we gave the ColBERT paradigm the name "late interaction" instead of "multi-vector", a term that emerged later and that has proven to be more intuitive. **The mechanism is actually not about having multiple vectors at all.** You can see this in four different ways. 🧵1/7

170

Omar Khattab @lateinteraction.bsky.social · 01/02/2025

Someone needs to write the book “Modern Machine Learning — the math, the myth, the legend”

1120

Omar Khattab @lateinteraction.bsky.social · 28/01/2025

a statistician walks into an error bar surprisingly, not everyone was mean to him

272

Omar Khattab @lateinteraction.bsky.social · 05/01/2025

What do you call LLMs that exhibit reward hacking for translation? Agents gone ROUGE.

3230

Omar Khattab @lateinteraction.bsky.social · 31/12/2024

Reminder to self: Much like a good paper always starts with (i) the status of the field at the time of the proposal, (ii) what’s an annoying gap, and (iii) the novel intuition that motivates a new insightful proposal, a good course lecture must also situate every major concept this way. [1/3]

1110

Omar Khattab @lateinteraction.bsky.social · 31/12/2024

When building ColBERT, I sort of assumed it will pave the way for hypernetwork-based, pruning-capable retrieval indexes. Let me explain. The big insight in ColBERT is that we can encode each document upfront *not* into a vector, but into a rich scoring function, f: query -> float, which ... [1/3]

1223

Reposted by Omar Khattab

Ana Marasović @anamarasovic.bsky.social · 29/12/2024

Anyone here have experience with working with someone in @aclmeeting.bsky.social to get a confirmation of reviewing/awards/etc for the purpose of US work visa / green card? If so, please can you share their contact with me 🙏

032

Reposted by Omar Khattab

Drew Breunig @dbreunig.bsky.social · 29/12/2024

Strongly agree. Especially when you need to be nimble enough to adopt new or different models.

031

Reposted by Omar Khattab

Yoav Goldberg @yoavgo.bsky.social · 29/12/2024

"prompt engineering" is much more about effective processes for creating good prompts for your data, than it is about specific techniques. which is to a large extent why platforms like dspy work: they kinda force you into a processes, while attempting to automate the techniques.

2186

Reposted by Omar Khattab

Drew Breunig @dbreunig.bsky.social · 27/12/2024

Using an LLM and DSPy to generate a glossary from my Jekyll site: www.dbreunig.com/2024/12/27/g...

dbreunig.com

Generating a Glossary from a Jekyll Blog Using DSPy & Claude

Asking LLMs to take the first pass at an AI glossary for my site.

161

Reposted by Omar Khattab

Hersh Gupta @hershgupta.com · 14/12/2024

City 311 employees spend a lot of time parsing service requests. To make this easier, I built a proof-of-concept that uses DSPy and vision models (like LLaVA) to augment 311 workflows: 📝: hershgupta.com/posts/smarte... 💻: github.com/hersh-gupta/...

hershgupta.com

Building Smarter 311 Systems with Vision Models | Hersh Gupta

Hersh Gupta is a data scientist working in municipal government

031

Reposted by Omar Khattab

Drew Breunig @dbreunig.bsky.social · 12/12/2024

Really enjoy DSPy’s workflow for LLM work. Handing off the specifics of prompt generation and engineering back to the LLM makes a lot of sense: www.dbreunig.com/2024/12/12/p...

dbreunig.com

Pipelines & Prompt Optimization with DSPy

Writing about technology, culture, media, data, and all the ways they interact.

1237

Reposted by Omar Khattab

Stanford NLP Group @stanfordnlp.bsky.social · 04/12/2024

Natural Language Processing—artificial intelligence that uses human language—has been on a roll lately. You’ve probably noticed! So the Stanford NLP Group has been growing, and diversifying into lots of new topics, including agents, language model programs, and socially aware #NLP. nlp.stanford.edu

Group picture of people in the Stanford NLP Group gathered in front of the shores of Lake Tahoe.

1538

Reposted by Omar Khattab

Ramesh Manuvinakurike @rameshddrr.bsky.social · 04/12/2024

Listening to this awesome talk from @cgpotts.bsky.social .. so in love with the message here .. As I'm building systems the most common questions (and review comments) I get asked is about the LL(M)M I'm using and not the systems and the problems they're solving .. youtu.be/vRTcE19M-KE?...

youtu.be

273

Reposted by Omar Khattab

Ramesh Manuvinakurike @rameshddrr.bsky.social · 04/12/2024

Dspy + Gradio + Huggingface = Magic !!

051

Reposted by Omar Khattab

merve @merve.bsky.social · 27/11/2024

The authors of ColPali trained a retrieval model based on SmolVLM 🤠 TLDR; - ColSmolVLM performs better than ColPali and DSE-Qwen2 on all English tasks - ColSmolVLM is more memory efficient than ColQwen2 💗 Find the model here huggingface.co/vidore/colsm...

4738

Omar Khattab @lateinteraction.bsky.social · 24/11/2024

machine learning has taught me that there are truly many ways to ablate a cat

1170

Omar Khattab @lateinteraction.bsky.social · 20/11/2024

With only 35 followers at this point, there may never be a better time for posting puns than right now.

1290

Reposted by Omar Khattab

Andrew Drozdov @mrdrozdov.com · 20/11/2024

Mat is not on 🦋—posting on his behalf! It's time to revisit common assumptions in IR! Embeddings have improved drastically, but mainstream IR evals have stagnated since MSMARCO + BEIR. We ask: on private or tricky IR tasks, are rerankers better? Surely, reranking many docs is best?

A plot showing that reranking improves recall as we increase the number of reranked docs, but with increasing docs we diminishing returns and eventually a performance dip.

48224