sunny madra (@sundeep) 's Twitter Profile
sunny madra

@sundeep

GM GroqCloud, prev co-f (@definitiveio acq. by @groqInc, autonomic acq. by @ford, and xtreme labs acq. by pivotal/@vmware), angel investor.

ID: 81278776

calendar_today10-10-2009 04:18:43

21,21K Tweet

22,22K Followers

3,3K Following

sunny madra (@sundeep) 's Twitter Profile Photo

One of the most exciting aspects of AI today is the rapid development and deployment of new ideas, along with the open exchange of information and diverse problem-solving approaches

Andrej Karpathy (@karpathy) 's Twitter Profile Photo

It's a bit sad and confusing that LLMs ("Large Language Models") have little to do with language; It's just historical. They are highly general purpose technology for statistical modeling of token streams. A better name would be Autoregressive Transformers or something. They

Benjamin Klieger (@benjaminklieger) 's Twitter Profile Photo

g1 powered by Llama-3.1 70b on Groq Inc now has a gradio of app, built by AK! Find it on the GitHub. See below example of g1 on gradio using reasoning to solve the Strawberry problem, initially thinking there are 2 β€˜R’s, until re-examining and finding 3 β€˜R’s.

g1 powered by Llama-3.1 70b on <a href="/GroqInc/">Groq Inc</a> now has a gradio of app, built by <a href="/_akhaliq/">AK</a>! Find it on the GitHub.

See below example of g1 on gradio using reasoning to solve the Strawberry problem, initially thinking there are 2 β€˜R’s, until re-examining and finding 3 β€˜R’s.
elvis (@omarsar0) 's Twitter Profile Photo

g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chains. Seems like an interesting open project to create o1-like reasoning chains. It's not fancy but it's powered by a prompt that leverages role-playing, chain-of-thought prompting, formatting, and a bunch of

g1: Using Llama-3.1 70b on Groq to create o1-like reasoning chains.

Seems like an interesting open project to create o1-like reasoning chains.

It's not fancy but it's powered by a prompt that leverages role-playing, chain-of-thought prompting, formatting, and a bunch of