John Calcio’s Post

Munish Gandhi Spot on. To see LLMs driving real value for enterprise use case Agents will be the future that will help push the accuracy of output and automation beyond a threshold where next wave of AI products can be adopted. This will also enable to solve more complicated use cases. Definitely a great read for anyone working on LLMs/GenerativeAI.

Agent Workflow Vs LLM ChatBot: My Interpretation Agent Workflow: Multiple different calls going to a LLM to serve a single user request (Iterate, improve: replicates how humans think) Versus LLM Zero-Shot mode (Flawed Assumption/Goal: Inherently probabilistic AI can lead to deterministic output) Super interesting read which spurred my thinking: https://lnkd.in/gUxRzBdA AI experts: What do you think? Too simplistic a POV?

Here is 4 AI Agents strategies mentioned https://lnkd.in/gSCPVzds And Poe just got multiple bots in a single Conversation feature. https://lnkd.in/gmdth2bm Imagine your own set of different named bots to reflect, criticize, plan, and use the common/custom tools in your conversation thread.

This is a great time to start asking your internal teams how AI can transform your business. This significant investment by WWT will not only fuel our growth as one of the best solution providers in the world, but will also help our customers achieve their top outcomes.

Exciting times ahead

Many considerations for AI 2.0

I started a Substack where I write about AI and my approach to building applications on top of it, check out the first post here!

It’s one thing to whip up a prototype of a large language model application; it’s quite another to build a robust, scalable solution that addresses real-world needs and stands the test of time. Read more about how to manage generative AI projects effectively: https://hubs.la/Q02yx3KW0 #generativeai #genai #llms

Scale AI has announced the launch of .... SEAL Leaderboards, an innovative and expert-driven ranking system for large language models (LLMs). This initiative is a product of the Safety, Evaluations, and Alignment Lab (SEAL) at Scale, which is dedicated to providing neutral, trustworthy evaluations of AI models. The SEAL Leaderboards aim to address the growing need for reliable performance comparisons as LLMs become more advanced and widely utilized. With hundreds of LLMs, comparing their performance and safety has become increasingly challenging. Scale, a trusted third-party evaluator for leading AI labs, has developed the SEAL Leaderboards to rank frontier LLMs using curated private datasets that cannot be manipulated. These evaluations are conducted by verified domain experts, ensuring the rankings are unbiased and provide a true measure of model performance. Leaderboard: https://lnkd.in/dp24vEtx

GenAI large language models (LLM) are famous for making up stuff when they do not have direct knowledge of something (hallucination). One of the ways to deal with that is through Retrieval Augmented Generation (RAG). You can easily create an AI chatbot to query about your own data, with that LLMs will be able to answer questions based on your own specific data (local knowledge). You simply leverage the reasoning power of the LLM. In future posts, I plan to show the power of AI agents to solve complex tasks autonomously. In this repo https://lnkd.in/eKPjFUZB, I have created one simple AI chatbot using Streamlit UI and Llama-index. You can change the LLM to one you prefer.