Hi Harkirat Singh , How can I contact you ? You haven't mentioned any business email or something else anywhere.

How about you ?

I recently thought that I'm hallucinating, but now I know that x has a sound in it for specific actions (like profile refresh by scrolling down.)😂

This morning I scammed scammer's money and just finished pizza 🍕 with it 😂. Did I done anything wrong here ?🤷

We are talking to people who have hired or who are hiring from Peerlist.... and some stories and use cases that we came across just blew our minds!! If you know someone who is hiring, would love to talk to them and ask a few questions as a part of our user research! Reshare

Hey Fold , first of all amazing app and it's solving my big problem so for that kudos to the makers. Quick questions 1. Are you planning to bring link credit card facilities? 2. Why Paytm Payments Bank is not support and it's not even list of upcoming?

Hey Ankur Syal , I saw something in my notification history, is that correct 😅

hey all👋, Please someone help me to reach out Harkirat Singh

It's pretty simple if you think about it

Very excited to announce the GA (general availability) ✨. Join the waitlist if you find Maxim AI can be helpful for your organization at - getmaxim.ai/demo

We are super excited to partner with Maxim AI as Vaibhavi Gangwar and Akshay Deo announce the fundraise and general availability launch of their enterprise-grade evaluation and observability platform, setting new standards for AI application development. With the recent

🚀 and we are looking to collaborate with senior engineers :) - DM if this mission excites you.

Yeah so true 🤣, btw, We are bringing Claude 3.5 sonnet on Maxim AI very very soon so make sure to give it a try.

progress is addictive.

If you are building apps powered by #LLMs, I would love to chat and demo some fantastic things we have built to help you go to production faster cal.com/akshaydeo/maxi…

Evaluation Nugget 🤔 1/ 🧵 In RAG retrieval systems, we often need to evaluate how well our models rank documents. Let's explore some key metrics, focusing on graded relevance scores, where relevance is scored from 0 to 5.

Phew! I just wrapped up our monthly recap, and wow - we've been busy (so busy that I skipped writing these for a few months)! 🚀. We've shipped a ton of cool stuff lately. 💪

I'm sure you know you're doing stupidity, right?

1/ 🧠 COBBLER (COgnitive Bias Benchmark for Evaluating LLMs). This new benchmark tests large language models like GPT-4 on their ability to evaluate outputs—specifically focusing on cognitive biases. #AI #LLM #CognitiveBias

1/ 🚀 With the rise of long-context LLMs like Llama3.1 & GPT-4o supporting up to 1M tokens, many wonder if Retrieval-Augmented Generation (RAG) is still relevant.