Researchers from Meta built a new RAG approach that:- outperforms LLaMA on 16 RAG benchmarks.- has 30.85x faster time-to-first-token.- handles 16x larger context windows.- and it utilizes 2-4x fewer tokens.Here's the core problem with a typical RAG setup that Meta solves:Most of what we retrieve in RAG setups never actually helps the LLM.In classic RAG, when a query arrives:- You encode it into a vector.- Fetch similar chunks from vector DB.- Dump the retrieved context into the LLM.It typically works, but a ...

RT Avi Chawla (@_avichawla)4 must-know model training paradigms for ML engineers: https://t.co/G3KunNYswt ...

4 must-know model training paradigms for ML engineers: https://t.co/G3KunNYswt ...

RT Avi Chawla (@_avichawla)Agents forget everything after each task!Graphiti builds temporally-aware knowledge graphs for your AI agents.Integrating its MCP server with Claude/Cursor adds a powerful memory layer to all your AI interactions across apps.100% open-source with 18k+ stars! https://t.co/f7t4DIdsb8 ...

AI Agent Enhancement - Graphiti 构建了时间感知的知识图谱，为 AI Agents 提供记忆能力 [1] - Graphiti 的 MCP 服务器与 Claude/Cursor 集成，为所有 AI 交互添加了强大的记忆层 [1] Open Source & Community - 该项目是 100% 开源的，拥有超过 18k+ stars (18 thousand plus stars) [1]

GitHub repo: https://t.co/knIZDLAxPg(Don't forget to star 🌟) ...

Agents forget everything after each task!Graphiti builds temporally-aware knowledge graphs for your AI agents.Integrating its MCP server with Claude/Cursor adds a powerful memory layer to all your AI interactions across apps.100% open-source with 18k+ stars! https://t.co/f7t4DIdsb8 ...

RT Avi Chawla (@_avichawla)You're in an ML Engineer interview at Netflix.The interviewer asks:"You’ve trained a new recommendation model.How do you make sure it’s ready to replace the old one?"You reply: "I’ll compare metrics on validation and test sets."Interview over.Here’s what you missed:The issue is that, despite rigorously testing an ML model locally (on validation and test sets), it could be a terrible idea to instantly replace the previous model with the new model.This is because it is difficult to ...

You're in an ML Engineer interview at Netflix.The interviewer asks:"You’ve trained a new recommendation model.How do you make sure it’s ready to replace the old one?"You reply: "I’ll compare metrics on validation and test sets."Interview over.Here’s what you missed:The issue is that, despite rigorously testing an ML model locally (on validation and test sets), it could be a terrible idea to instantly replace the previous model with the new model.This is because it is difficult to replicate the exact product ...

AI Agent Framework - Google launched ADK, an open-source framework for building, orchestrating, evaluating, and deploying production-grade Agentic systems [1] - Google ADK is compatible with MCP (for connecting to external tools), A2A (for connecting to other agents), and AG-UI (for connecting to users) [1] AG-UI Protocol - AG-UI is an open-source protocol enabling agents to collaborate with users [2] - AG-UI facilitates a bridge between a backend AI agent and a full-stack app [2] - Connecting an agent to a React frontend using CopilotKit involves defining the agent with ADK and connecting it to the frontend [2]