RT Avi Chawla (@_avichawla)DevOps vs. MLOps vs. LLMOps:Many teams are trying to apply DevOps practices to LLM apps.But DevOps, MLOps, and LLMOps solve fundamentally different problems.DevOps is software-centric. You write code, test it, and deploy it. The feedback loop is straightforward: Does the code work or not?MLOps is model-centric. Here, you're dealing with data drift, model decay, and continuous retraining. The code might be fine, but the model's performance can degrade over time because the world ch ...

DevOps vs. MLOps vs. LLMOps:Many teams are trying to apply DevOps practices to LLM apps.But DevOps, MLOps, and LLMOps solve fundamentally different problems.DevOps is software-centric. You write code, test it, and deploy it. The feedback loop is straightforward: Does the code work or not?MLOps is model-centric. Here, you're dealing with data drift, model decay, and continuous retraining. The code might be fine, but the model's performance can degrade over time because the world changes.LLMOps is foundation- ...

RT Avi Chawla (@_avichawla)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 processI've done this on a LightningAI studio, and you can reproduce everythin ...

@LightningAI 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. https://t.co/55NJmdW6tVAvi Chawla (@_avichawla):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> https://t.co/6sYZj4q0AI ...

Clone the @LightningAI studio to get started: https://t.co/1XntPP86Az ...

LLM Development & Training - The report introduces a method to build a modern LLM from scratch using Karpathy's nanochat, emphasizing its clean, minimal, and hackable codebase [1] - The process involves training a tokenizer, pre-training for next-word prediction, mid-training for conversational abilities, and SFT (fine-tuning) on high-quality dialogue datasets [1] - Evaluation and logging are integral to every step of the LLM development process [1] Implementation & Accessibility - The method can be reproduced with a single click on a LightningAI studio, requiring zero setup [1]

RT Avi Chawla (@_avichawla)Devs often treat Agent context as an access problem.The thinking goes like this:"If there's no API, just scrape the website. And if scraping breaks, let the Agent use the browser like a human."This sounds reasonable until you try to run it in production.To see why, consider a simple task:"Watch this site and notify me when the price changes."Without an API, the Agent has to infer meaning from HTML, layouts, and UI behavior.But if a pop-up appears or the DOM shifts, then suddenly, ...

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. https://t.co/ocO8UZkuFaAvi Chawla (@_avichawla):Devs often treat Agent context as an access problem.The thinking goes like this:"If there's no API, just scrape the website. And if scraping breaks, let the Agent use the browser like a human."This sounds reasonable until you try to run it in production.To see why, https://t.co/mq7APfuOH6 ...

Postman's guide on solving the API problem: https://t.co/5HwGFY72oC ...

Devs often treat Agent context as an access problem.The thinking goes like this:"If there's no API, just scrape the website. And if scraping breaks, let the Agent use the browser like a human."This sounds reasonable until you try to run it in production.To see why, consider a simple task:"Watch this site and notify me when the price changes."Without an API, the Agent has to infer meaning from HTML, layouts, and UI behavior.But if a pop-up appears or the DOM shifts, then suddenly, the Agent is clicking the w ...