BREAKING : Grok3 Reasoning outperforms o3-mini-high. The Smartest AI on Earth at this moment
OPEN SOURCE
-
Grok-3 hits 1400+ score milestone
By
–
Chocolate on @lmarena_ai was Grok 3! The first model to hit a 1400+ score Grok-3 is also being trained continuously
-
Open Source AI Model: o3-mini vs Phone-Optimized Deployment
By
–
for our next open source project, would it be more useful to do an o3-mini level model that is pretty small but still needs to run on GPUs, or the best phone-sized model we can do?
-
31 Production-Ready RAG Implementations with LangChain
By
–
Advanced RAG Techniques Discover a powerful collection of 31 production-ready RAG implementations, from basic to advanced, built with LangChain. Each technique comes with detailed documentation and practical code examples to enhance your RAG systems. Level up your RAG
-
LangChain RAG Doc Assistant Built with LangGraph Orchestration
By
–
LangChain Doc Assistant A powerful RAG system for querying LangChain docs, built with LangGraph orchestration. Available as both a live service and reference implementation, it features source-backed answers and customizable models. Build your own doc assistant today!
-
Secure RAG Systems with LangChain and OpenFGA Authorization
By
–
Secure RAG with OpenFGA Build secure RAG systems with document-level authorization using LangChain and OpenFGA. The FGARetriever implementation provides:
– Authorization layer
– Vector store integration
– RAG pipeline Learn how to implement it: https://
auth0.com/blog/building-
a-secure-rag-with-python-langchain-and-openfga/
… -
Safe AI Agent Tutorial: Blockchain Operations with LangChain
By
–
Safe AI Agent Tutorial Create AI agents that handle Safe wallet operations and smart contracts using LangChain. This open-source guide shows how to combine blockchain interactions with intelligent agents. AI wallet agent https://
github.com/5afe/safe-ai-a
gent-tutorial
… -
TorchTune Library Growth Inspired by LitGPT
By
–
Oh yeah, torchtune is a good library. It was modeled after our LitGPT library and has grown quite a bit!
-
Drop-in replacement code for modified attention mechanism available
By
–
Yup, the reader posted the code for a drop-in replacement for the modified attention mechanism. Just copy and paste it into the Chapter 5 code, which is available in the GitHub repo linked above.
-
Merging Query and Key Weight Matrices in LLM Training
By
–
Can we merge the query and key weight matrices in an LLM into a single covariance matrix and still train effectively? Here are some promising early results from a reader: https://
github.com/rasbt/LLMs-fro
m-scratch/discussions/517
…
Anyone else familiar with projects that tried this?