Coffee Sessions #150

The Future of Search in the Era of Large Language Models

Saahil shares insights into the You.com search engine approach, which includes a focus on a user-friendly interface, third-party apps, and the combination of natural language processing and traditional information retrieval techniques. Saahil highlights the importance of product thinking and the trade-offs between relevance, throughput, and latency when working with large language models. Saahil also discusses the intersection of traditional information retrieval and generative models and the trade-offs in the type of outputs they produce. He suggests occupying users' attention during long wait times and the importance of considering how users engage with websites beyond just performance.

Take-aways

- Main Takeaway: The search landscape is rapidly changing due to a confluence of exciting advancements in natural language processing (NLP) and generative AI. - Fundamentals of search systems: we can chat about fundamental properties of search systems, starting with terminology (classical information retrieval, semantic search, generative AI). - Recent innovations in search & open challenges: Topics here can span information retrieval, machine learning, benchmarking search (some studies we’ve conducted there - opportunities & pitfalls), data collection, multi-modal search, recently released LLMs like ChatGPT, and the potential/pitfalls of generative AI within search. - Machine learning at a rapidly growing startup: We can chat a bit about what it is like working as an engineer at a small startup taking on big companies in a competitive space. I can compare to previous experiences working at big companies (e.g. Microsoft). - YouChat: You.com recently released YouChat, a ChatGPT-like model as part of our search engine that provides up-to-date data and citations. I’d be happy to discuss what impact these kind of large language models have on search and the way users find information. At this point, I can’t disclose technical details of our model, but I can talk about practical use cases. - Open Platform: we’re building an open platform that allows developers to build their applications on top of the You.com search engine and display their apps to users within our search engine. This might be interesting to developers, data scientists, and practitioners working on their own projects and looking for ways to get exposure. - AI Tools for Engineering: I can talk about different AI tools for engineering, using examples from YouCode (our search engine for developers). We have various models that allow users to generate code from text. We can chat about how code language models will make engineers more efficient.

In this episode

Saahil Jain

Saahil Jain

Engineer, You.com

Saahil Jain is an engineer at You.com. At You.com, Saahil builds searching and ranking systems. Previously, Saahil was a graduate researcher in the Stanford Machine Learning Group under Professor Andrew Ng, where he researched topics related to deep learning and natural language processing (NLP) in resource-constrained domains like healthcare. His research work has been published in machine learning conferences such as EMNLP, NeurIPS Datasets & Benchmarks, and ACM-CHIL among others. He has publicly released various machine learning models, methods, and datasets, which have been used by researchers in both academic institutions and hospitals across the world, as part of an open-source movement to democratize AI research in medicine. Prior to Stanford, Saahil worked as a product manager at Microsoft on Office 365. He received his B.S. and M.S. in Computer Science at Columbia University and Stanford University respectively.

Twitter

LinkedIn

Demetrios Brinkmann

Demetrios Brinkmann

Host

Demetrios is one of the main organizers of the MLOps community and currently resides in a small town outside Frankfurt, Germany. He is an avid traveller who taught English as a second language to see the world and learn about new cultures. Demetrios fell into the Machine Learning Operations world, and since, has interviewed the leading names around MLOps, Data Science, and ML. Since diving into the nitty-gritty of Machine Learning Operations he felt a strong calling to explore the ethical issues surrounding ML. When he is not conducting interviews you can find him making stone stacking with his daughter in the woods or playing the ukulele by the campfire.

David Aponte

David Aponte

Host

David is one of the organizers of the MLOps Community. He is an engineer, teacher, and lifelong student. He loves to build solutions to tough problems and share his learnings with others. He works out of NYC and loves to hike and box for fun. He enjoys meeting new people so feel free to reach out to him!