Yu next posed the question of whether operating LLMs (LLMOps) would continue to be a part of MLOps, or if it would be a new discipline. Wu posited that there would be a mix of use cases: calling out to APIs for "closed" foundation models vs. Luu referred to a recent blog post by DoorDash's Head of AI, which identified five usage areas Luu elaborated on the use case of LLMs as digital assistants. Ramanathan predicted that there would be two broad categories of use: low-risk scenarios, such as internal document retrieval and higher risk scenarios, where LLMs would likely be used as a "copilot" rather than acting autonomously. Yu began by asking panelists their opinions of the future of LLMs in production and how they will be used. The panelists discussed questions about large language models (LLMs) posed by Yu and fielded a few more from the audience at the end of the session.
engineering manager at DoorDash and Rishab Ramanathan, co-founder & CTO of Openlayer. Panelists included Sherwin Wu, a member of technical staff at OpenAI Hien Luu, Sr. The panel was moderated by Bozhao (Bo) Yu. The recent QCon New York conference featured a panel discussion titled " Navigating the Future: LLM in Production." Some key takeaways are that there are two trends in LLMS: closed models behind APIs and open-source models, and that organizations using LLMs will need to think deeply about testing and evaluating the models themselves, with a strong emphasis on risk mitigation.
0 kommentar(er)
