Workflow
Avi Chawla
icon
Search documents
X @Avi Chawla
Avi Chawla· 2025-10-26 06:31
If you found it insightful, reshare it with your network.Find me → @_avichawlaEvery day, I share tutorials and insights on DS, ML, LLMs, and RAGs. ...
X @Avi Chawla
Avi Chawla· 2025-10-26 06:31
GitHub repo: https://t.co/rqVrQGaKAG(don't forget to star it ⭐ ) ...
X @Avi Chawla
Avi Chawla· 2025-10-26 06:31
9 real-world MCP projects for AI engineers covering:- RAG- Memory- MCP client- Voice Agent- Agentic RAG- and much more!Find them in the GitHub repo below. https://t.co/oXp4PmxvYB ...
X @Avi Chawla
Avi Chawla· 2025-10-25 06:31
You're in an ML Engineer interview at Apple.The interviewer asks:"Two models are 88% accurate.- Model A is 89% confident.- Model B is 99% confident.Which one would you pick?"You: "Any would work since both have same accuracy."Interview over.Here's what you missed:Modern neural networks can be misleading.They are overconfident in their predictions.For instance, I saw an experiment that used the CIFAR-100 dataset to compare LeNet with ResNet.LeNet produced:- Accuracy = ~0.55- Average confidence = ~0.54ResNet ...
X @Avi Chawla
Avi Chawla· 2025-10-24 06:32
If you found it insightful, reshare it with your network.Find me → @_avichawlaEvery day, I share tutorials and insights on DS, ML, LLMs, and RAGs.Avi Chawla (@_avichawla):Let's build a reasoning LLM using GRPO, from scratch (100% local): ...
X @Avi Chawla
Avi Chawla· 2025-10-24 06:32
Finally, I'll leave you with an overview of the GRPO process.Let me know what other techniques you have used in the comments!You can find all the code and everything you need on the @LightningAI⚡️Studio here:https://t.co/LkqLLCLHg7 https://t.co/ThsF4xp8uf ...
X @Avi Chawla
Avi Chawla· 2025-10-24 06:31
Let's build a reasoning LLM using GRPO, from scratch (100% local): ...
X @Avi Chawla
Avi Chawla· 2025-10-23 20:02
Core Concept of Memento - Memento reframes continual learning as memory-based online reinforcement learning over a memory-augmented MDP, learning from experiences using memory instead of updating LLM weights [2] - Memento aims to improve AI agent performance from experience without fine-tuning LLM weights [1] Key Components - Case-Based Reasoning (CBR) decomposes complex tasks into sub-tasks and retrieves relevant past experiences [2] - Executor executes each subtask using MCP tools and records outcomes in memory for future reference [3] MCP Tools - MCP tools enable the executor to accomplish most real-world tasks [3] - MCP tools include Web research, Document handling, Safe Python execution, Data analysis, and Media processing [3]
X @Avi Chawla
Avi Chawla· 2025-10-23 06:30
GitHub repo: https://t.co/rr7SR2ALEL ...
X @Avi Chawla
Avi Chawla· 2025-10-23 06:30
Fine-tuning LLM Agents without Fine-tuning LLMs!Imagine improving your AI agent's performance from experience without ever touching the model weights.It's just like how humans remember past episodes and learn from them.That's precisely what Memento does.The core concept:Instead of updating LLM weights, Memento learns from experiences using memory.It reframes continual learning as memory-based online reinforcement learning over a memory-augmented MDP.Think of it as giving your agent a notebook to remember wh ...