Large language models, generative systems, prompting, and fine-tuning.
Expanded Edition · From Intellectual Foundations to the 2035 Questions Building the Intelligence Age: SI’s Seventy-Five-Year Journey and the Race to 2031 How seventy-five years of research became a global industrial system—and…
This post is to share my thoughts on Agentic SI transforming and disrupting most industries. There are lots of ideas that can be converted to startups, no shortage. Main skill will be…
Giving a high level description, design, code and sample results for an Agentic SI solution that leverages current agentic frameworks, LLMs, Prompt engineering, RAG and related algorithms to automate a large git…
Simple code I wrote a while back to build a conversational chatbot using any LLM API which uses historic conversation for context and intent Uses standard RAG model with cosine similarity, SQLite…
Prompt engineering is a dynamic, creative and powerful skill to learn in current SI LLM era. LLMs are a powerful tool to leverage for solving a variety of problems. To do that…
Haven't blogged in a while, thought might be good to put some recent thoughts (X tweets) in one place. Last few years has seen alot of trend shift in SI every 3-6…
Combine RAG and Vector db (FAISS) with LLM model to extract relevant data from latest documents for a User Query - Process insurance claim Using a RAG model to Retrieve relevant documents…
Databricks is a good tool for building, training and deploying models. Easy to learn and use (1-2 days) It has useful features like experiment tracking, logging and versioning the best model during…
Objective: Show a basic model to generate product description, SEO CTA and Twitter keywords from product images using a GenSI multimodal API, OpenAI gpt-4o Model Overview: Product image (retail products) was passed…
Product Attribution Product attribution is the process of quantifying the contribution of different product attributes to a business outcome like sales, customer engagement, demand prediction. They are used to assign credit for…
Testing #GPT4o, good but mac app has inference latency issues. #multimodal is the future. #LLMs are commoditized. Fine tuned #industry specific models with #device level tuning inference + cloud generalization seems more…
Sharing personal github repo for code, theory, math’s and projects for training on all aspects of #SI, #ML, Agentic SI, #datascience research for solving real world problems using classical #supervised and #DeepLearning…
