TheSequence

TheSequence

Home
Archive
About

February 2025

The Sequence Research #500: Making Small Models Great Achieve GPT-o1 Levels in Math Reasoning with Microsoft rStar-Math
The new method represents an important evolution of reasoning for SLMs.
The Sequence Opinion #499: Reinforcement Learning was Dying and then Gen AI Came Along
Some perspectives about how foundation models inspired a new era in reinforcement learning.
The Sequence Engineering #498: Integrating Tools with AI Agents Using Composio
Hundreds of connectors that can be integrated using a simple programming framework.
The Sequence Knowledge #497: Microsoft's GraphRAG is One of the Newest RAG Techniques
The methods enables RAG in an interconnected graph of documents
📖 Mastering LLM Inference
[Free Guidebook]
The Sequence Radar #496: Microsoft Muse Can Generate Entire Games After Watching You Play
The new AI model represents a milestone in gameplay idetation.
The Sequence Research #495: Microsoft's Framework for Building Large Action Models
An architecture reference and framework for building models that can execute actions.
The Sequence Opinion #494: Models that Learn All the Time? Some Cutting Edge Ideas about Continual Learning
Modularity, sparcity, MoEs and other ideas that can unlock continual learning.
The Sequence Engineering #493: One of the Best Agent Frameworks in the Market Just Got Way Better
The new version adds a considerable set of capabilities for a more integrated agent development experience.
The Sequence Knowledge #492: RAG-Fusion is Better than Just RAG
Understanding the principles of RAG-fusion techniques.
© 2025 Jesus Rodriguez
Privacy ∙ Terms ∙ Collection notice
Start WritingGet the app
Substack is the home for great culture