Shreya Shankar

Join Willem Pienaar, CTO of Cleric and creator of Feast, along with PhD student Shreya Shankar, as they tackle the toughest challenges in building AI agents. They discuss the ambiguity of 'ground truth' in evaluations, revealing three key gulfs of human-AI interaction that hinder success. The duo emphasizes the importance of moving humans out of the feedback loop, using implicit signals for faster learning. Practical techniques like heat maps for task failures and the complexities of simulated environments are also explored, shedding light on the inevitable performance ceiling of AI.

Shreya Shankar, a PhD student at UC Berkeley specializing in intelligent data processing, shares her insights on the innovative DocETL system. They discuss how this technology optimizes LLM-powered data pipelines, enhancing analysis of complex documents. Shreya highlights the challenges of data extraction from PDFs, the importance of human feedback in AI systems, and the need for tailored benchmarks in data processing. Real-world applications and the future of agentic systems are also examined, showcasing a visionary path in data management.

About This EpisodeShreya Shankar is a computer scientist, PhD student in databases at UC Berkeley, and co-author of "Operationalizing Machine Learning: An Interview Study", an ethnographic interview study with 18 machine learning engineers across a variety of industries on their experience deploying and maintaining ML pipelines in production.Shreya explains the high-level findings of "Operationalizing Machine Learning"; variables that indicate a successful deployment (velocity, validation, and versioning), common pain points, and a grouping of the MLOps tool stack into four layers. Shreya and Lukas also discuss examples of data challenges in production, Jupyter Notebooks, and reproducibility.Show notes (transcript and links): http://wandb.me/gd-shreya---💬 *Host:* Lukas Biewald---*Subscribe and listen to Gradient Dissent today!*👉 Apple Podcasts: http://wandb.me/apple-podcasts​​👉 Google Podcasts: http://wandb.me/google-podcasts​👉 Spotify: http://wandb.me/spotify​

Shreya Shankar, a PhD student in EECS at UC Berkeley, dives into how Large Language Models (LLMs) are changing the game for unstructured enterprise data. She explains her innovative framework, DocETL, which streamlines semantic extraction and thematic analysis of text and PDFs. The conversation touches on the practical challenges of data extraction and the evolution towards multimodal processing with tools like DocWrangler. Shreya also highlights the importance of aligning user intent with model capabilities for better user experiences.

Experts from Amazon, Hex, Modal, Parlance Labs, and UC Berkeley share lessons learned from working with Large Language Models. They discuss the importance of evaluation and monitoring in LLM applications, data literacy in AI, the fine-tuning dilemma, real-world insights, and the evolving roles of data scientists and AI engineers.