#BardAI hard fail! Travelling and need a negative COVID test 48 hours before Frankfurt flight #GenerativeAI seemed great for figuring out buffer time But looks like BARD failed miserably...It didn't realize Frankfurt is ahead of ATL! It also can't subtract 48 hours!

Empower your customers with generative AI! Learn how companies can use AI to summarize info, answer questions, simulate customer dialogues, and more in this blog post: #GenerativeAI #AI #GPT4 medium.com/p/70297f1c9698

LLM Economics: ChatGPT vs Open-Source by Skanda Vivek buff.ly/3oJGi0C

When Should You Fine-Tune LLMs? by Skanda Vivek buff.ly/42GbcGc

Small perks of being a dad!

OpenAI introduced "function calling" that has the potential to completely transform how we write code and interact with machines. 🔄💡💻 Imagine querying databases using unstructured prompts on instead of SQL! Curious? 🤔💡Check out my blog post! pub.towardsai.net/how-openais-ne…

Models like ChatGPT/GPT-4 work great in many use cases, but there are many reasons companies are exploring open-source LLMs including: - Data, privacy concerns with closed APIs - Domain specific use-cases Read more in my blog! #LLM #opensouce #NLP medium.com/@skanda-vivek/…

(How) will generative #AI change education? GoTech Research Scholar Skanda Vivek argues that reasoning is where humans shine & AI fails making it a weakness that educators can exploit to reduce cases of misuse. Check out the GoTech Insights blog post: buff.ly/3OcPNyj

Daughter's art for a project - yes, we love libraries in this house 😊

Explore recent research into Self-RAG, a novel approach that boosts the performance of "vanilla" RAG, by following along Skanda Vivek's accessible writeup. buff.ly/3QWVxio

🚀 Exciting News in the Vector DB Space! 🚀 Upstash has recently introduced its own flavor of vector DB, offering a delightful balance between ease of usage and visually appealing analytics of performance. 🚀💻 See my blog for more! medium.com/p/5ae96e6fb51c

Learn how to: 🔍 Extract text from PDFs 🧩 Chunk documents for LLM processing 🔑 Implement both keyword-based retrieval (Okapi BM25) and vector embeddings The best part? We build everything from the ground up! No prior RAG experience needed. 💪 skandavivek.substack.com/p/your-first-r…