top of page
To fine-tune or not to fine tune (and do retrieval instead)
In the world of Large Language Models, how do we leverage this technology to answer questions that are domain specific or can behave in a certain way? In this talk, we’ll compare and contrast the fine tuning of a large language model from using retrieval to augment our generated responses with the power of a vector database from an LLM.
An engineer with nearly a decade of experience in the industry tackling large scale IDE deployments at Apple, widespread adoption of conversational messaging interfaces between businesses and consumers at Google, and now working in the AI space helping developers across the globe build scalable, production ready AI applications fast.
bottom of page