The Stack Overflow Podcast
Improving error monitoring with AI
Mar 18, 2025
Tillman Elser, Engineering Manager for AI and ML at Sentry, shares his journey from economic research to cutting-edge tech. He dives into how semantic embeddings, especially using BERT, revolutionize error monitoring by transforming complex stack traces into actionable insights. The discussion also sheds light on enhancing customer engagement in data labeling akin to an escape room challenge. Finally, Tillman highlights breakthroughs in error monitoring tools, showcasing the impact of generative AI in ensuring security and privacy for developers.
27:29
Episode guests
AI Summary
AI Chapters
Episode notes
Podcast summary created with Snipd AI
Quick takeaways
- The guest's transition from an early career in economics to a focus on coding and machine learning exemplifies the evolving paths in tech careers.
- Sentry's innovative use of AI for error monitoring categorizes stack traces, enhancing debugging efficiency and allowing developers to prioritize critical issues.
Deep dives
The Journey into AI and ML
The guest shares a diverse background, having studied computer science and economics, and worked at the Federal Reserve Board. His early career involved interesting projects like forecasting interest in treasury debt auctions, which combined coding with economics. However, he found his passion primarily in coding and machine learning, leading to his current role at Sentry. This shift illustrates a common trajectory for many in tech, where early experiences set the stage for a more focused career in software development and AI.
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
