Dhruv (@_dhruvbhardwaj_) 's Twitter Profile
Dhruv

@_dhruvbhardwaj_

learning LLMs by building them from scratch.

Building Agents for Legal Workflows at infiny.ai

ID: 1455191526699515913

linkhttps://www.infiny.ai/ calendar_today01-11-2021 15:14:39

589 Tweet

207 Followers

824 Following

Paras Chopra (@paraschopra) 's Twitter Profile Photo

if you're a teenager or young, your biggest strategic lever is that your cost of failure is basically close to zero. so use it to your advantage. take career risks. try building a startup. you'd have such a long adulthood to recover that a few years of failing here and there

Dhruv (@_dhruvbhardwaj_) 's Twitter Profile Photo

So true, the first thing i built was a gym workout tracker app which contains all my workout templates so that I dont have to use Strong and struggle with just 3 templates.

Dhruv (@_dhruvbhardwaj_) 's Twitter Profile Photo

We will he at the India AI Summit! Excited to be a part and meet curious people. If you will be there as well then let me know!

Dhruv (@_dhruvbhardwaj_) 's Twitter Profile Photo

So i have to fill a form in Azure to deploy gpt5.2 and basically every decent model? Microsoft Azure Feels like early 2020 when you had to fill the OpenAI to get access to text-davinci-003 :/

Sebastian Raschka (@rasbt) 's Twitter Profile Photo

While waiting for DeepSeek V4 we got two very strong open-weight LLMs from India yesterday. There are two size flavors, Sarvam 30B and Sarvam 105B model (both reasoning models). Interestingly, the smaller 30B model uses “classic” Grouped Query Attention (GQA), whereas the

While waiting for DeepSeek V4 we got two very strong open-weight LLMs from India yesterday.

There are two size flavors, Sarvam 30B and Sarvam 105B model (both reasoning models).

Interestingly, the smaller 30B model uses “classic” Grouped Query Attention (GQA), whereas the