[GUEST ACCESS MODE: Data is scrambled or limited to provide examples. Make requests using your API key to unlock full data. Check https://lunarcrush.ai/auth for authentication information.]

@akshay_pachaar Avatar @akshay_pachaar Akshay 🚀

Akshay 🚀 posts on X about ai, opensource, open ai, token the most. They currently have XXXXXXX followers and XX posts still getting attention that total XXXXXXX engagements in the last XX hours.

Engagements: XXXXXXX #

Engagements Line Chart

Mentions: XX #

Mentions Line Chart

Followers: XXXXXXX #

Followers Line Chart

CreatorRank: XXXXXXX #

CreatorRank Line Chart

Social Influence #

Social category influence technology brands XXXX% social networks XXXX% stocks #2154 finance XXXX%

Social topic influence ai #2483, opensource #2, open ai #61, token 6.45%, youtube 3.23%, llm #102, repo #100, accounting 1.61%, the project 1.61%, limits XXXX%

Top accounts mentioned or mentioned by @akshaypachaar @zepai @avichawla @milvusio @assemblyai @firecrawldev @_avichawla @daniavila7s @freecodecamp @ggerganov @crewaiinc @cometml @coreyms @metaalchemist @reparodynamics @grok @ameliadacine @codewithimanshu @neuwarkai @sumanth_077

Top assets mentioned Alphabet Inc Class A (GOOGL) Microsoft Corp. (MSFT)

Top Social Posts #

Top posts by engagements in the last XX hours

"If anyone needs a video guide to Karpathy's nanochat check out Stanford's CS336 It covers: - Tokenization - Resource Accounting - Pretraining - Finetuning (SFT/RLHF) - Overview of Key Architectures - Working with GPUs - Kernels and Tritons - Parallelism - Scaling Laws - Inference - Evaluation - Alignment Everything you need to prepare for a job at Frontier AI Labs. I'm taking this course and will share my learnings here on X. Link to the playlist in the next tweet"
X Link @akshay_pachaar 2025-10-14T16:47Z 232.9K followers, 118.5K engagements

"Claude Skills might be the biggest upgrade to AI agents so far Some say it's even bigger than MCP. I've been testing skills for the past 3-4 days and they're solving a problem most people don't talk about: agents just keep forgetting everything. In this video I'll share everything I've learned so far. It covers: The core idea (skills as SOPs for agents) Anatomy of a skill Skills vs. MCP vs. Projects vs. Subagents Building your own skill Hands-on example Skills are the early signs of continual learning and they can change how we work with agents forever Here's everything you need to know:"
X Link @akshay_pachaar 2025-10-27T14:32Z 232.9K followers, 277.2K engagements

"uv is the best thing that has happened to Python devs And you won't find a better cheatsheet than this:"
X Link @akshay_pachaar 2025-10-18T17:20Z 232.9K followers, 102.4K engagements

"Turn messy PDFs into clean LLM-ready data Dolphin revolutionizes document image parsing with its analyze-then-parse approach making complex documents accessible to AI applications. Handles text tables formulas & figures. XXX% open-source lightning-fast solution"
X Link @akshay_pachaar 2025-10-22T12:33Z 232.9K followers, 41.4K engagements

"Building AI agents dont read blogs dont watch videos write code and build things from scratch I've open-sourced 90+ projects on AI Agent RAG MCP and context engineering (18k+ stars already) GitHub:"
X Link @akshay_pachaar 2025-10-26T16:35Z 232.9K followers, 47.4K engagements

"Context engineering in Claude Skills is GENIUS Skills use a 3-layer context management system that lets it use 100s of skills without hitting context limits. Here's how it works: Layer 1: Main Context - Always loaded it contains the project configuration. Layer 2: Skill Metadata - Comprises only the YAML frontmatter about 2-3 lines ( XXX tokens). Layer 3: Active Skill Context - SKILL. md files and associated documentation are loaded as needed. Supporting files like scripts and templates aren't pre-loaded but accessed directly when in use consuming zero tokens. This architecture supports"
X Link @akshay_pachaar 2025-10-28T14:28Z 232.9K followers, 115.5K engagements

"A XXX% open-source alternative to n8n Sim is a drag-and-drop UI for creating powerful AI agent workflows: - Runs locally on your machine - Works with local LLMs I built a job finder for top YC startups & connected it to Telegram in minutes. Here's a step-by-step guide:"
X Link @akshay_pachaar 2025-08-28T13:08Z 232.9K followers, 122.9K engagements

"I just built an open NotebookLM clone Here's what it can do for you: - Process multi-modal data - Scrape websites and YouTube videos - Create a unified knowledge base - Lets you do RAG over it - Remember every conversation - Generate a podcast 🎙 The idea here is not to reinvent the wheel but to understand how one of the most powerful tools for learning and research actually works by building it step-by-step So by the end of this video you'll learn how to: Process multimodal data (text audio video URLs and YouTube videos) into a format ready for LLMs Store everything in a vector database for"
X Link @akshay_pachaar 2025-10-17T12:43Z 232.9K followers, 73.6K engagements

"if you're looking for a comprehensive guide to LLM finetuning check this a free 115-page book on arxiv covering: fundamentals of LLM peft (lora qlora dora hft) alignment methods (ppo dpo grpo) mixture of experts (MoE) 7-stage fine-tuning pipeline multimodal finetuning & challenges industrial frameworks (hf sagemaker openai) everything you need to know in one place download link in the replies"
X Link @akshay_pachaar 2025-10-19T14:36Z 232.9K followers, 55.3K engagements

"You're in an ML Engineer interview at OpenAI. The interviewer asks: "Our GPT model generates XXX tokens in XX seconds. How do you make it 5x faster" You: "I'll optimize the model architecture and use a better GPU." Interview over. Here's what you missed:"
X Link @akshay_pachaar 2025-10-20T12:30Z 232.9K followers, 185.9K engagements

"I built my own ChatGPT from scratch and you can too. karpathy's nanochat is a single clean minimal and hackable codebase to build a modern LLM. By setting this up you'll learn how to: train a tokenizer from the ground up pre-training: master next-word prediction mid-training: teach the model to hold conversations sft: fine-tune on high-quality dialogue datasets evaluate and log every step of the process I've done this on a LightningAI studio and you can reproduce everything with a single click (zero setup required). link in the next tweet"
X Link @akshay_pachaar 2025-10-21T12:30Z 232.9K followers, 40.7K engagements

"Finally A Text-to-SQL tool that actually works Vanna is an open-source RAG framework for complex Text-to-SQL generation. It manages dynamic data and allows custom RAG model training for greater accuracy. XXX% open-source"
X Link @akshay_pachaar 2025-10-24T12:30Z 232.9K followers, 83.7K engagements

"While everyone's vibecoding a few truly understand what's actually happening. This roadmap matters more now than ever. So let's dive in 🚀"
X Link @akshay_pachaar 2025-10-25T12:32Z 232.9K followers, 4479 engagements

"1 Python bootcamp by @freeCodeCamp X hours Python bootcamp with over 46M views It covers: - Installing Python - Setting up an IDE - Basic Syntax - Variables & Datatypes - Looping in Python - Exception handling - Modules & pip - Mini hands-on projects Check this out👇"
X Link @akshay_pachaar 2025-10-25T12:32Z 232.9K followers, 4873 engagements

"4 Corey Schafer Arguably the best Python channel on YouTube. This channel focuses on tutorials and walkthroughs for SDEs programmers and engineers. Check this out👇"
X Link @akshay_pachaar 2025-10-25T12:32Z 232.9K followers, 3180 engagements

"STOP duct-taping your AI pipeline together. Pixeltable is a unified declarative framework that handles your entire multimodal pipeline from data storage to model execution. Seamlessly manage images videos text and tabular data all in one place. XXX% open-source"
X Link @akshay_pachaar 2025-10-29T13:17Z 232.9K followers, 17.6K engagements

"LLM fine-tuning techniques I'd learn if I were to customize them: Bookmark this. X. LoRA X. QLoRA X. Prefix Tuning X. Adapter Tuning X. Instruction Tuning X. P-Tuning X. BitFit X. Soft Prompts X. RLHF XX. RLAIF XX. DPO (Direct Preference Optimization) XX. GRPO (Group Relative Policy Optimization) XX. RLAIF (RL with AI Feedback) XX. Multi-Task Fine-Tuning XX. Federated Fine-Tuning My favourite is GRPO for building reasoning models. What about you I've shared my full tutorial on GRPO in the replies"
X Link @akshay_pachaar 2025-10-08T13:15Z 232.8K followers, 82.8K engagements

"Challenge 1) Notice this pattern at the start of training: - The model selects "Expert 2" - The expert gets a bit better - It may get selected again - The expert learns more - It gets selected again - It learns more - And so on Many experts go under-trained"
X Link @akshay_pachaar 2025-10-13T12:36Z 232.8K followers, 2847 engagements

"We solve this in two steps: - Add noise to the feed-forward output of the router so that other experts can get higher logits. - Set all but top K logits to -infinity. After softmax these scores become zero. This way other experts also get the opportunity to train"
X Link @akshay_pachaar 2025-10-13T12:36Z 232.8K followers, 2510 engagements

"Thus to generate a new token we only need the hidden state of the most recent token. None of the other hidden states are required. Next let's see how the last hidden state is computed within the transformer layer from the attention mechanism"
X Link @akshay_pachaar 2025-10-20T12:30Z 232.8K followers, 6092 engagements

"During attention: The last row of query-key-product involves: - the last query vector. - all key vectors. Also the last row of the final attention result involves: - the last query vector. - all key & value vectors. Check this visual to understand better:"
X Link @akshay_pachaar 2025-10-20T12:30Z 232.8K followers, 4667 engagements

"The above insight suggests that to generate a new token every attention operation in the network only needs: - query vector of the last token. - all key & value vectors. But there's one more key insight here"
X Link @akshay_pachaar 2025-10-20T12:30Z 232.7K followers, 3682 engagements

"Links: - FreeCodeCamp: - Deep Learning: - Harvard: - Corey: - Project learning: Learn MCPs from scratch (with XX projects):"
X Link @akshay_pachaar 2025-10-25T12:32Z 232.8K followers, 5929 engagements

"If you found it insightful reshare with your network. Find me @akshay_pachaar ✔ For more insights and tutorials on LLMs AI Agents and Machine Learning"
X Link @akshay_pachaar 2025-10-25T12:32Z 232.8K followers, 6767 engagements

"@meta_alchemist Absolutely Glad you liked it"
X Link @akshay_pachaar 2025-10-28T03:54Z 232.7K followers, XXX engagements

"@_avichawla I would add to this the AG-UI protocol. MCP: Agents to tools A2A: Agents to agents AG-UI: Agents to users"
X Link @akshay_pachaar 2025-10-29T06:48Z 232.8K followers, 1992 engagements

"Google just dropped a new LLM You can run it locally on just XXX GB RAM. Let's fine-tune this on our own data (100% locally):"
X Link @akshay_pachaar 2025-08-15T12:38Z 232.9K followers, 2M engagements

"8 key skills to become a full-stack AI Engineer:"
X Link @akshay_pachaar 2025-09-07T13:21Z 232.9K followers, 498.3K engagements

"So let's dive in and understand how KV caching works.👇"
X Link @akshay_pachaar 2025-10-20T12:30Z 232.9K followers, 8502 engagements

"To understand KV caching we must know how LLMs output tokens. - Transformer produces hidden states for all tokens. - Hidden states are projected to the vocab space. - Logits of the last token are used to generate the next token. - Repeat for subsequent tokens. Check this👇"
X Link @akshay_pachaar 2025-10-20T12:30Z 232.9K followers, 7986 engagements

"DeepSeek just dropped a new OCR model And this isn't about OCR. We've all heard "a picture is worth a thousand words." DeepSeek literally proved it. They've built a breakthrough in AI memory compression that could change how models handle long contexts. The core idea: Instead of storing every word as a token take a picture of the text and compress it into vision tokens. - XXX vision tokens 1000 text tokens (10 compression at XX% accuracy) - XX vision tokens 1000 text tokens (60% accuracy) Why does this matter LLMs struggle with long context windows. Processing millions of tokens is expensive"
X Link @akshay_pachaar 2025-10-21T07:42Z 232.9K followers, 25.8K engagements

"Dolphin GitHub:"
X Link @akshay_pachaar 2025-10-22T12:33Z 232.9K followers, 4167 engagements

"5 Project-based learning This GitHub repo contains a curated list of great Python projects across many domains and areas of interest. It has 225k stars Check this out👇"
X Link @akshay_pachaar 2025-10-25T12:32Z 232.9K followers, 2890 engagements

"@_avichawla Absolutely I also tried their PixelBot an agent orchestration system built on top of Pixeltable. It provides unified storage for data state and memory. Exactly what context engineering demands"
X Link @akshay_pachaar 2025-10-29T13:31Z 232.8K followers, XXX engagements

"@_avichawla Voyage models are really good no doubt. I used their voyage-context-3 recently and their quantized 512d model was better than OpenAI 3072 full precision model"
X Link @akshay_pachaar 2025-10-30T06:54Z 232.9K followers, 1626 engagements

"Every LangGraph user I know is making the same mistake They all use the popular supervisor pattern to build conversational agents. The pattern defines a supervisor agent that analyzes incoming queries and routes them to specialized sub-agents. Each sub-agent handles a specific domain (returns billing technical support) with its own system prompt. This works beautifully when there's a clear separation of concerns. The problem is that it always selects just one route. For instance if a customer asks: "I need to return this laptop. Also what's your warranty on replacements" The supervisor routes"
X Link @akshay_pachaar 2025-10-30T12:31Z 232.9K followers, 118.5K engagements

"@Reparodynamics Love how you described it lucid"
X Link @akshay_pachaar 2025-10-30T12:48Z 232.9K followers, XXX engagements

"I've been coding in Python for X years now. If I were to start over today here's a complete roadmap:"
X Link @akshay_pachaar 2025-10-25T12:32Z 232.9K followers, 64.3K engagements

"Microsoft did it again Building with AI agents almost never works on the first try. You spend days tweaking prompts adding examples hoping it gets better. Nothing systematic just guesswork. This is exactly what Microsoft's Agent Lightning solves. It's an open-source framework that trains ANY AI agent with reinforcement learning. Works with LangChain AutoGen CrewAI OpenAI SDK or plain Python. Here's how it works: Your agent runs normally with whatever framework you're using. Just add a lightweight agl.emit() helper or let the tracer auto-collect everything. Agent Lightning captures every"
X Link @akshay_pachaar 2025-10-31T12:30Z 232.9K followers, 145.7K engagements

"Link to the GitHub repo: (don't forget to star 🌟)"
X Link @akshay_pachaar 2025-10-31T12:30Z 232.9K followers, 12.5K engagements