Krista Opsahl-Ong
@kristahopsalong
Followers
2K
Following
449
Media
7
Statuses
81
AI research @DbrxMosaicAI || Prev @Stanford @StanfordAILab @Google @Microsoft
Stanford, CA
Joined January 2012
Got a pipeline with **multiple prompts**, like a DSPy program? What's the right way to jointly optimize these prompts?. Introducing MIPRO, a Multi-prompt Instruction Proposal Optimizer. We integrated MIPRO into DSPy. It can deliver +11% gains over existing DSPy optimizers!. 🧵👇
16
86
484
RT @jefrankle: Not that I have a favorite recent project, but. 🧵 LLM judges are the popular way to evaluate generative models. But they h….
0
14
0
RT @alexrtrott: Ever wonder what it'd look like if an LLM Judge and a Reward Model had a baby? So did we, which is why we created PGRM -- t….
0
25
0
RT @matei_zaharia: Really excited about ALHF, new work from our research team that lets users give natural language feedback to agents and….
0
31
0
RT @bemikelive: Since joining @databricks, our research team has been hard at work on Agent Bricks, a new product that helps enterprises de….
databricks.com
Discover how Agent Learning from Human Feedback (ALHF) powers Databricks Agent Bricks, enabling AI agents like Knowledge Assistant to adapt to expert expectations with minimal natural language...
0
19
0
RT @LakshyAAAgrawal: Prof. Yann LeCun has now christened GEPA settling any debate on it's pronunciation!.
0
4
0
RT @jefrankle: RLVR isn't just for math and coding! At @databricks, it's impacting products and users across domains. One example: SQL Q&A.….
0
15
0
RT @LakshyAAAgrawal: Paper: GEPA will be open-sourced soon as a new DSPy optimizer. Stay tuned!. Incredibly gratef….
0
17
0
RT @abeirami: There is a rich set of research questions in design and optimization of agentic workflows with a ton of room for theoretical….
0
11
0
RT @BrandoHablando: 🚨 Can your LLM really do math—or is it cramming the test set?. 📢 Meet Putnam-AXIOM, a advanced mathematics contaminatio….
0
21
0
Really cool work! And great seeing our new optimizer SIMBA out in the wild 🦁.
🤯 New research deploys DSPy-optimized system in real-world medical settings. Finds 70% increase in positive patient feedback. The authors introduce Dr.Copilot, a multi-agent DSPy assistant in Romanian. Optimized along 17 axes like Empathy & Explanations using dspy.SIMBA.
2
6
47
RT @lateinteraction: The #SIGIR2025 Best Paper just awarded to the WARP engine for fast late interaction!. Congrats to Luca Scheerer🎉 WARP….
0
32
0
Come to our @databricks booth at #ICML if you want to chat about the path to building real AI systems reliably, sustainably, and at scale 🚀.
I'm at ICML 🇨🇦 and I'm hiring at @databricks. Visit our booth if you're interested. My scientific focus: It's 1972 in AI, there's an AI crisis, Dijkstra isn't here to save us, and maybe RL can. Why Databricks? The long road to AGI is being paved here and we have the real evals 🧵.
1
0
14
I’ll be at #ICML this week! ✈️🇨🇦 . Excited to chat with folks about DSPy, automatic prompt optimization methods, compound AI systems, and research roles at Databricks (we’re hiring!). If these topics interest you, feel free to reach out or find me at the Databricks booth!.
5
9
100
RT @CShorten30: Congratulations to @lateinteraction and the @DSPyOSS team! DSPy 3.0!! 🚀. Continuing to push the frontier for building AI so….
0
22
0
Agent Bricks is officially launched! 🤖🧱 It's been incredibly fun working on these products with the rest of @DbrxMosaicAI & the @databricks engineering team. Excited to see what folks are able to build with them!.
Excited to launch Agent Bricks, a new way to build auto-optimized agents on your tasks. Agent Bricks uniquely takes a *declarative* approach to agent development: you tell us what you want, and we auto-generate evals and optimize the agent.
1
5
76
Highly recommend this @DeepLearningAI course by @ChenMoneyQ as a way to learn about DSPy & how you can leverage it to build & optimize agents! 🤖⭐. Chen did a phenomenal job crafting these lessons with helpful hands-on tutorials. Let us know what you think! 🧩.
New short course: DSPy: Build and Optimize Agentic Apps. DSPy is a powerful open-source framework for automatically tuning prompts for GenAI applications. In this course, you'll learn to use DSPy, together with MLflow. This is built in partnership with @databricks and taught by
0
8
49
RT @ivanzhouyq: Great to see a collaboration between @AndrewYNg, @databricks and @DSPyOSS ! 🌟.@DSPyOSS is a powerful and thoughtful framewo….
0
9
0
RT @lateinteraction: If you're in SF in 2 weeks, see you at the @Databricks Data + AI Summit, where we have a long list of sessions on @DSP….
0
28
0
RT @michaelryan207: And be sure to check out our updated camera ready paper: “Optimizing Instructions and Demonstrations for Multi-Stage La….
0
5
0