A look at some of the current thinking around chunking data for retrieval-augmented generation (RAG) systems. https://stackoverflow.blog/2024/06/06/breaking-up-is-hard-to-do-chunking-in-rag-applications/
Learn about the workflow designed to help new askers improve their questions on Stack Overflow. https://stackoverflow.blog/2024/06/04/introducing-staging-ground-the-private-space-to-get-feedback-on-questions-before-they-re-posted/
This week we chat with Kamakshi Narayan, Director of Product Management at SnapLogic, who is focused on how APIs can apply fine-grained controls for privacy and governance to the LLM-powered AI apps vacuuming up our data. https://stackoverflow.blog/2024/06/04/how-to-prevent-your-new-chatbot-from-giving-away-company-secrets/
Today's episode is a chat with Benjamin Shestakofsky, an assistant professor of sociology at the University of Pennsylvania with a focus on the ways in which digital technologies are affecting work and employment, organizations, and economic exchange. We discuss research from his new book which dives into the venture capital business and explores the cooperative model that some software startups are taking instead. https://stackoverflow.blog/2024/05/31/can-software-startups-that-need-cash-avoid
We also asked when and how often CodeGen tools fall short, what challenges developers face with these tools, and what they are doing with all of the free time these tools purport to offer. https://stackoverflow.blog/2024/05/29/developers-get-by-with-a-little-help-from-ai-stack-overflow-knows-code-assistant-pulse-survey-results/
Temporal is an open-source project focused on durable execution and workflow orchestration. Cofounder and CTO Maxim Fateev tells Ben and Ryan about the challenges of building a cloud service based on an open-source project and how Temporal is helping teams simplify their code and build more features more quickly. https://stackoverflow.blog/2024/05/28/an-open-source-development-paradigm/
Ben and Ryan are joined by Robin Gupta for a conversation about benchmarking and testing AI systems. They talk through the lack of trust and confidence in AI, the inherent challenges of nondeterministic systems, the role of human verification, and whether we can (or should) expect an AI to be reliable. https://stackoverflow.blog/2024/05/24/would-you-board-a-plane-safety-tested-by-genai/
A developer’s journal is a place to define the problem you’re solving and record what you tried and what worked. https://stackoverflow.blog/2024/05/22/you-should-keep-a-developer-s-journal/
Ben and Ryan talk with Vikram Chatterji, founder and CEO of Galileo, a company focused on building and evaluating generative AI apps. They discuss the challenges of benchmarking and evaluating GenAI models, the importance of data quality in AI systems, and the trade-offs between using pre-trained models and fine-tuning models with custom data. https://stackoverflow.blog/2024/05/21/how-to-train-your-dream-machine/
This year we are asking familiar questions about your experience, but also have some new questions about what embedded programming technology you are using and what AI ethical responsibilities are most important to you. https://stackoverflow.blog/2024/05/20/the-good-the-bad-and-the-disruptive-let-us-know-where-you-stand-in-the-2024-annual-developer-survey/
