Applied Large Language Models with Vishwas Lele
How do we put large language models to work? Carl and Richard talk to Vishwas Lele about his work using LLMs with his customers. Vishwas talks about focusing on specific data sets for building LLMs and how size matters - things are simple when the source data is small, but as it grows, you need more complex tools to be able to allow the LLM to perform. Lots of cautionary tales and ideas on how to get great results from these new automation tools!
Guests:
Vishwas Lele
Vishwas Lele serves as CTO at Applied Information Sciences, Inc. Mr. Lele is responsible for assisting organizations in envisioning, designing and implementing enterprise solutions related cloud and mobility. Mr. Lele brings close to 25 years of experience and thought leadership to his position, and has been with AIS for 20 years. A noted industry speaker and author, Mr. Lele serves as the Microsoft Regional Director for Washington D.C. and is currently a Microsoft Azure MVP.
Links:
- The AI Bot Show https://theaibotshow.com
- Vector Search in Azure Cognitive Services https://learn.microsoft.com/azure/search/vector-search-overview?WT.mc_id=DT-MVP-10953
- Microsoft 365 Copilot https://blogs.microsoft.com/blog/2023/03/16/introducing-microsoft-365-copilot-your-copilot-for-work/
- Vishwas' Post on Othello GPT https://www.linkedin.com/posts/vlele_performing-brain-mris-on-large-language-models-activity-7109302309125332992-3xak/