[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.]

# ![@_avichawla Avatar](https://lunarcrush.com/gi/w:26/cr:twitter::1175166450832687104.png) @_avichawla Avi Chawla

Avi Chawla posts on X about llms, opensource, $googl, for your the most. They currently have XXXXXX followers and XX posts still getting attention that total XXXXXX engagements in the last XX hours.

### Engagements: XXXXXX [#](/creator/twitter::1175166450832687104/interactions)
![Engagements Line Chart](https://lunarcrush.com/gi/w:600/cr:twitter::1175166450832687104/c:line/m:interactions.svg)

- X Week XXXXXXX -XX%
- X Month XXXXXXXXX -XX%
- X Months XXXXXXXXXX +152%
- X Year XXXXXXXXXX +8,306%

### Mentions: XX [#](/creator/twitter::1175166450832687104/posts_active)
![Mentions Line Chart](https://lunarcrush.com/gi/w:600/cr:twitter::1175166450832687104/c:line/m:posts_active.svg)

- X Week XX -XX%
- X Month XX -XX%
- X Months XXX +181%
- X Year XXX +1,892%

### Followers: XXXXXX [#](/creator/twitter::1175166450832687104/followers)
![Followers Line Chart](https://lunarcrush.com/gi/w:600/cr:twitter::1175166450832687104/c:line/m:followers.svg)

- X Week XXXXXX +0.43%
- X Month XXXXXX +3%
- X Months XXXXXX +103%
- X Year XXXXXX +1,959%

### CreatorRank: XXXXXXX [#](/creator/twitter::1175166450832687104/influencer_rank)
![CreatorRank Line Chart](https://lunarcrush.com/gi/w:600/cr:twitter::1175166450832687104/c:line/m:influencer_rank.svg)

### Social Influence [#](/creator/twitter::1175166450832687104/influence)
---

**Social category influence**
[stocks](/list/stocks)  XXXX% [technology brands](/list/technology-brands)  XXXX%

**Social topic influence**
[llms](/topic/llms) #25, [opensource](/topic/opensource) #43, [$googl](/topic/$googl) 2.63%, [for your](/topic/for-your) 2.63%, [should be](/topic/should-be) 2.63%, [rates](/topic/rates) 2.63%, [llm](/topic/llm) 2.63%, [token](/topic/token) 2.63%, [generator](/topic/generator) 2.63%, [meta](/topic/meta) XXXX%

**Top accounts mentioned or mentioned by**
[@akshaypachaar](/creator/undefined) [@akshay_pachaar](/creator/undefined) [@suhrabautomates](/creator/undefined) [@ronald_vanloon](/creator/undefined) [@1__________l1l_](/creator/undefined) [@otto_katz_456](/creator/undefined) [@whitewoodcity](/creator/undefined) [@freedrthug](/creator/undefined) [@realmikeescarn](/creator/undefined) [@_junaidkhalid1](/creator/undefined) [@duru_tobe](/creator/undefined) [@catsu_curry](/creator/undefined) [@lmdc45](/creator/undefined) [@clark24_bennet](/creator/undefined)

**Top assets mentioned**
[Alphabet Inc Class A (GOOGL)](/topic/$googl)
### Top Social Posts [#](/creator/twitter::1175166450832687104/posts)
---
Top posts by engagements in the last XX hours

"I've been coding in Python for X years now. If I were to start over today here's a complete roadmap:"  
[X Link](https://x.com/_avichawla/status/1968926369599078503) [@_avichawla](/creator/x/_avichawla) 2025-09-19T06:33Z 52.9K followers, 221K engagements


"Finally someone fixed LLM hallucinations Parlant lets you build Agents that do not hallucinate and actually follow instructions. One of the things that makes this possible is the new reasoning approach that the open-source Parlant framework uses. Detailed explainer below:"  
[X Link](https://x.com/_avichawla/status/1980359702602215825) [@_avichawla](/creator/x/_avichawla) 2025-10-20T19:45Z 52.9K followers, 56.4K engagements


"Figma canvas to build AI agent workflows. Sim is a lightweight user-friendly platform for building AI agent workflows in minutes. It natively supports all major LLMs Vector DBs etc. XXX% open-source with 7k+ stars"  
[X Link](https://x.com/_avichawla/status/1957691571908038717) [@_avichawla](/creator/x/_avichawla) 2025-08-19T06:30Z 52.9K followers, 81.8K engagements


"DeepMind built a simple RAG technique that: - reduces hallucinations by XX% - improves answer relevancy by XX% Let's understand how to use it in RAG systems (with code):"  
[X Link](https://x.com/_avichawla/status/1958053890831872065) [@_avichawla](/creator/x/_avichawla) 2025-08-20T06:30Z 52.9K followers, 668.7K engagements


"Google did it again First they launched ADK a fully open-source framework to build orchestrate evaluate and deploy production-grade Agentic systems. And now they have made it even powerful Google ADK is now fully compatible with all three major AI protocols out there: - MCP: To connect to external tools - A2A: To connect to other agents - AG-UI: To connect to users. AG-UI is the newest addition which is an open-source protocol that enables agents to collaborate with users. They worked with the AG-UI team to build this. It takes just two steps: - Define the agent with ADK with its tools state"  
[X Link](https://x.com/_avichawla/status/1975811218763096199) [@_avichawla](/creator/x/_avichawla) 2025-10-08T06:31Z 52.9K followers, 164.2K engagements


"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. XXX% open-source with 18k+ stars"  
[X Link](https://x.com/_avichawla/status/1976536015969120312) [@_avichawla](/creator/x/_avichawla) 2025-10-10T06:31Z 52.9K followers, 58.6K engagements


"This should be impossible You can clean any ML dataset in just three lines of code. Flag outliers find label errors and more across: - Any data (tabular text image etc.) - Any task (classification entity recognition etc.) XXX% open-source built by MIT researchers"  
[X Link](https://x.com/_avichawla/status/1977629357108867396) [@_avichawla](/creator/x/_avichawla) 2025-10-13T06:55Z 52.9K followers, 29.2K engagements


"A great tool to estimate how much VRAM your LLMs actually need. Alter the hardware config quantization etc. it tells you about: - Generation speed (tokens/sec) - Precise memory allocation - System throughput etc. No more VRAM guessing"  
[X Link](https://x.com/_avichawla/status/1978710362557235495) [@_avichawla](/creator/x/_avichawla) 2025-10-16T06:31Z 52.9K followers, 22K engagements


"Youre in an ML Engineer interview at Stripe. The interviewer asks: "People often dispute transactions they actually made. How to build a supervised model that predicts fake disputes Theres no labeled data." You: "I'll flag cards with high dispute rates." Interview over. Here's what you missed: Active learning is a relatively easy and inexpensive way to build supervised models when you dont have annotated data to begin with. As the name suggests the idea is to build the model with active human feedback on examples it is struggling with. The visual below summarizes this. 1) Begin by manually"  
[X Link](https://x.com/_avichawla/status/1979072665194500539) [@_avichawla](/creator/x/_avichawla) 2025-10-17T06:31Z 52.9K followers, 40.3K engagements


"Keras now lets you quantize models with just one line of code You can either quantize your own models or any pre-trained model obtained from KerasHub. Simply run model.quantize(quantization_mode). Supports quantization to int4 int8 float8 and GPTQ modes"  
[X Link](https://x.com/_avichawla/status/1979435056251965809) [@_avichawla](/creator/x/_avichawla) 2025-10-18T06:31Z 52.9K followers, 20.6K engagements


"Finally researchers have open-sourced a new reasoning approach that actually prevents hallucinations in LLMs. It beats popular techniques like Chain-of-Thought and has a SOTA success rate of 90.2%. Here's the core problem with current techniques that this new approach solves: We have enough research to conclude that LLMs often struggle to assess what truly matters in a particular stage of a long multi-turn conversation. For instance when you give Agents a 2000-word system prompt filled with policies tone rules and behavioral dos and donts you expect them to follow it word by word. But heres"  
[X Link](https://x.com/_avichawla/status/1980159925109309799) [@_avichawla](/creator/x/_avichawla) 2025-10-20T06:31Z 52.9K followers, 88.9K engagements


"The open-source RAG stack (2025):"  
[X Link](https://x.com/_avichawla/status/1980521956446462455) [@_avichawla](/creator/x/_avichawla) 2025-10-21T06:30Z 52.9K followers, 42.5K engagements


"3 vLLM vLLM is a fast and easy-to-use library for LLM inference and serving. It provides state-of-the-art serving throughput With a few lines of code you can locally run LLMs as an OpenAI-compatible server. Check this out👇"  
[X Link](https://x.com/_avichawla/status/1927251156239016373) [@_avichawla](/creator/x/_avichawla) 2025-05-27T06:30Z 52.9K followers, 6218 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](https://x.com/_avichawla/status/1949356680871067925) [@_avichawla](/creator/x/_avichawla) 2025-07-27T06:30Z 52.9K followers, 19.3K engagements


"@akshay_pachaar The AI Agent Builder is actually really useful. Most of my MCP servers that involve public APIs come from its MCP Generator. Select the tools you need and it automatically creates the MCP server for you:"  
[X Link](https://x.com/_avichawla/status/1973097180110925995) [@_avichawla](/creator/x/_avichawla) 2025-09-30T18:46Z 52.9K followers, 1608 engagements


"You're in an ML Engineer interview at Netflix. The interviewer asks: "Youve trained a new recommendation model. How do you make sure its ready to replace the old one" You reply: "Ill compare metrics on validation and test sets." Interview over. Heres 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 production environment and conditions locally and justify success with val/test accuracies. A"  
[X Link](https://x.com/_avichawla/status/1976173787621331207) [@_avichawla](/creator/x/_avichawla) 2025-10-09T06:32Z 52.9K followers, 68.7K engagements


"A time-complexity cheat sheet of XX ML algorithms: What's the inference time-complexity of KMeans"  
[X Link](https://x.com/_avichawla/status/1978353875494240260) [@_avichawla](/creator/x/_avichawla) 2025-10-15T06:54Z 52.9K followers, 32.8K engagements


"Try it here"  
[X Link](https://x.com/_avichawla/status/1978710374540341407) [@_avichawla](/creator/x/_avichawla) 2025-10-16T06:31Z 52.9K followers, 1802 engagements


"Researchers from Meta built a new RAG approach that: - outperforms LLaMA on XX 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 at a huge cost: - Most chunks contain irrelevant text. - The LLM has to process"  
[X Link](https://x.com/_avichawla/status/1977260787027919209) [@_avichawla](/creator/x/_avichawla) 2025-10-12T06:31Z 52.9K followers, 99.6K engagements


"Here's a neural net optimization trick that leads to 4x faster CPU to GPU transfers. Imagine an image classification task. - We define the network load the data and transform it. - In the training loop we transfer the data to the GPU and train. Here's the problem with this: If you look at the profiler: - Most of the time/resources will be allocated to the kernel (the actual training code). - However a significant amount of time will also be dedicated to data transfer from CPU to GPU (this appears under cudaMemcpyAsync). Reducing the data transfer is simple. Recall that the original dataset"  
[X Link](https://x.com/_avichawla/status/1979797527772930278) [@_avichawla](/creator/x/_avichawla) 2025-10-19T06:31Z 52.9K followers, 36.9K engagements


"10 MCP AI Agents and RAG projects for AI Engineers (with code):"  
[X Link](https://x.com/_avichawla/status/1911306413932163338) [@_avichawla](/creator/x/_avichawla) 2025-04-13T06:32Z 52.9K followers, 698.9K engagements


"How LLMs work clearly explained (with visuals):"  
[X Link](https://x.com/_avichawla/status/1942472125484523605) [@_avichawla](/creator/x/_avichawla) 2025-07-08T06:33Z 52.9K followers, 745.6K engagements


"KV caching is a technique used to speed up LLM inference. Before understanding the internal details look at the inference speed difference in the video: - with KV caching X seconds - without KV caching XX seconds (5x slower) Let's dive in"  
[X Link](https://x.com/_avichawla/status/1949356658658005482) [@_avichawla](/creator/x/_avichawla) 2025-07-27T06:30Z 52.9K followers, 22.3K engagements


"Finally Python XXXX lets you disable GIL It's a big deal because earlier even if you wrote multi-threaded code Python could only run one thread at a time giving no performance benefit. But now Python can run your multi-threaded code in parallel. And uv fully supports it"  
[X Link](https://x.com/_avichawla/status/1977985594103140710) [@_avichawla](/creator/x/_avichawla) 2025-10-14T06:31Z 52.9K followers, 547.3K engagements


"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 what worked and what didn't How does it work The system breaks down into two key"  
[X Link](https://x.com/_avichawla/status/1981246733322768780) [@_avichawla](/creator/x/_avichawla) 2025-10-23T06:30Z 52.9K followers, 30.2K engagements