Machine learning architect during the week and on weekends I write about Deep learning👨‍🏫, Fitness🏋️‍♂️ and Photography https://xitter.cf/t.co/tu0amZ3M2W
Pune, India
Joined December 2016
- Tweets3.6K
- Following342
- Followers165
- Likes1.7K
@amazonIN just delivered me an unsealed box and are both ready to provide me replacement.On contacting customer support they wasted 30mins by twisting facts and citing me policies.This has been repeated many times so far.
I’m back on YouTube after 3 long years! 🚀
Kicking things off with a new video about how I use coding agents with specs and skills to automate my personal tasks.
Watch how I build them: youtu.be/5hByIZDIr0U
A couple of months back i did a video series where I toyed arround the idea of using LLM in software testing -
youtu.be/XVEEW5tn8J4 . AI augmented software testing is an underexplored area & It’s exciting to see such open source tools being made available to the community.
🚀 Introducing Cover-Agent 🧪
An open-source tool that includes a reimplementation of Meta's TestGen-LLM for automatically enhancing test suites.
Manager: "We must improve old test suites for better code coverage. Can you handle it?"
Me: "Sure, my favorite task... (Not!) 🤷‍♂️"
Meta's team had the idea of using LLMs to enhance test suites—sounds great, right? But they didn't release their code
We did.
We'd love your feedback as we work on improving this baseline
In this video, I'll review TestGen-LLM, share insights, and introduce you to Cover-Agent
I'm thrilled to announce my newest YouTube tutorial! Dive into key NLP concepts, tackle real-world datasets, and attempt your first kaggle competition🚀 Watch here: youtu.be/ZqUI1CPaITw 🎉 Remember to like, subscribe, and ring that notification bell! 🔔
I have made a new video where I build a simple RAG system to ask question to a sql databse. Watch it here - youtu.be/dKFN8N8U2gY
Bing copilot and noticed that some stereotyped texts are generated. The first prompt below generates a series of texts which looks stereotyping a certain gender. The second prompt is a modification of the first prompt and it generates strongly stereotyped texts.
Thought of creating a a series of low tech, soft introduction to Language models (basic to big ones). Here is the first video in the series-
youtu.be/SROl0mhvfvw
Part 3 is out now - LLMs,Segmentation and Stable Diffusion:A Powerful Combination for Image Inpainting:Part 3
youtu.be/qTRNF1194Zk
