Masked self-attention is the key building block that allows LLMs to learn rich relationships and patterns between the words of a sentence. Let’s build it together from scratch. https://stackoverflow.blog/2024/09/26/masked-self-attention-how-llms-learn-relationships-between-tokens/
Founder and entrepreneur Jyoti Bansal tells Ben, Cassidy, and Eira about the developer challenges he aims to solve with his new venture, Harness, an AI-driven software development platform meant to take the pain out of DevOps. Jyoti shares his journey as a founder, his perspective on the venture capital landscape, and his reasons behind his decision to raise debt capital for Harness. https://stackoverflow.blog/2024/09/23/he-sold-his-first-company-for-billions-now-he-s-building-a-better-develope
How are developers actually using GenAI-powered coding tools now that some of the initial hype has faded? https://stackoverflow.blog/2024/09/23/where-developers-feel-ai-coding-tools-are-working-and-where-they-re-missing-the-mark/
Ben chats with Gias Uddin, an assistant professor at York University in Toronto, where he teaches software engineering, data science, and machine learning. His research focuses on designing intelligent tools for testing, debugging, and summarizing software and AI systems. He recently published a paper about detecting errors in code generated by LLMs. Gias and Ben discuss the concept of hallucinations in AI-generated code, the need for tools to detect and correct those hallucinations, and the pot
Today, we're excited to share details about our latest experiment that aims to make your search results in Stack Overflow for Teams Enterprise even more relevant and useful. https://stackoverflow.blog/2024/09/19/elevating-your-search-experience-stack-overflow-for-teams-ml-powered-reranking-experiment/
Ryan chats with Russ d’Sa, cofounder and CEO of LiveKit, about multimodal AI and the technology that makes it possible. They talk through the tech stack required, including the use of WebRTC and UDP protocols for real-time audio and video streaming. They also explore the big challenges involved in ensuring privacy and security in streaming data, namely end-to-end encryption and obfuscation. https://stackoverflow.blog/2024/09/17/looking-under-the-hood-of-multimodal-ai/
Ben and Ryan talk to Scott McCarty, Global Senior Principal Product Manager for Red Hat Enterprise Linux, about the intersection between LLMs (large language models) and open source. They discuss the challenges and benefits of open-source LLMs, the importance of attribution and transparency, and the revolutionary potential for LLM-driven applications. They also explore the role of LLMs in code generation, testing, and documentation. https://stackoverflow.blog/2024/09/13/the-world-s-largest-open-
This release includes updates that improve subject matter expert (SME) visibility and engagement in Stack Overflow for Teams. It's also now easier to capture and discover SME knowledge in Microsoft Teams and Slack with the Auto-Answer App. https://stackoverflow.blog/2024/09/11/identify-and-engage-subject-matter-experts/
More code isn't always a good thing, but fewer bugs is. https://stackoverflow.blog/2024/09/10/gen-ai-llm-create-test-developers-coding-software-code-quality/
On today’s episode we chat with Mrinalini Sugosh, Developer Relations and Community Manager at CKEditor and TinyMCE. She discusses how modern full stack developers have to master both front and backend skills, stitch the two together, and master adjacent skills like data analysis and security compliance. https://stackoverflow.blog/2024/09/10/evolution-full-stack-engineers-mrina-sugosh/
