
step 1: build a computer use harness for system one step 2: train a system one model to output text so it can search and fill in text fields step 3: rl the model on cua trajectories step 4: let it rip

decisions, decisions, decisions

step 1: build a computer use harness for system one step 2: train a system one model to output text so it can search and fill in text fields step 3: rl the model on cua trajectories step 4: let it rip


Datetime outputs dates as ISO format. You can use it to ask questions about specific times and events.

Number allows queries to return numerical information inferred from images and text.

Use text to extract information from documents, websites, or images.

Use span to find specific sections in text relating to a query. When composed with classification, it can cite which parts of the input drove the decision, making the label easier to audit and trust.

We're announcing Mo-2.0 a frontier System One model with 8 output types for deciding and extracting. - choice - noul - score - box - span - text - number - datetime



If you thought this was interesting, we have some more gems for you... modaic.dev
The more I play around with GEPA the more I realize its not just a prompt optimization algorithm. Its really the most efficient way to have an LLM explore a massive dataset and and make useful insights. This visualizer alone shows just how cool that process is.

The more I play around with GEPA the more I realize its not just a prompt optimization algorithm. Its really the most efficient way to have an LLM explore a massive dataset and and make useful insights. This visualizer alone shows just how cool that process is.

Open source btw! github.com/modaic-ai/modaic/…
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/g… Here are some of the highlights that'll help you get past the DSPy learning curve faster 🧵

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

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 youtube.com/@Informationshel… to get the updates

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

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.
Agent scaffolds are as important as models.