Hi ,
ChatGPT was one of the best things to ever happen to data science - not so much because of what it can do, but because, virtually
overnight, it made AI and data science mainstream.
However, while most data scientists now have experience with ChatGPT and other large language model (LLM)-based technologies as end users, few have had experience in building their own LLM-based tools.
In the latest episode of Value Driven Data Science, I'm joined by TeamSolve Founder and CEO Dr Mudasser Iqbal to discuss the data science behind LLMs and how to go about doing just that.
Some of the things we discuss in this episode include:
- The data science behind LLMs.
- How TeamSolve's AI-powered chatbot, Lily, compares to ChatGPT and the advantages of a domain-specific, private chatbot, such as Lily, over a more general, public chatbot, such as ChatGPT.
- How knowledge graphs can be combined with LLMs to overcome many
of the shortcomings of LLMs.
- The changing attitudes of organisations around the use of generative AI.
- What the emergence of cutting-edge AI tools, such as LLMs, mean for more traditional data science tools, such as analytics dashboards.
- The future of generative AI, and the potential benefits and risks to society.
You can listen to this episode by clicking the button below, or find it on Apple Podcasts, Amazon Music, Spotify or Google Podcasts.
