Operations | Monitoring | ITSM | DevOps | Cloud

AI model drift is when an AI system's performance and accuracy degrades over time because the data, user behavior, or business environment has changed since the model was trained or evaluated. Even if latency, uptime, and infrastructure metrics remain healthy, model quality can quietly decline, leading to less accurate predictions, inconsistent responses, and reduced user trust.

BubbleUp has always been the fastest way to figure out what a group of outliers have in common. Draw a box around a band of slow traces, a cluster of errors, or any set of events you're interested in, and BubbleUp compares that selection to the baseline across every dimension you've sent us. It's how Honeycomb users find the "unknown unknowns" that dashboards can’t show you.

Last week, we sat down with the authors of Observability Engineering for a live AMA. We ended up getting so many questions (pre-submitted and live) that we couldn't get through them all. Charity, Liz, George, and Austin kindly stuck around afterward to answer more, ranging from low-hanging observability fruits and telemetry to AI and what software engineers can do that Claude can't. Missed the live session? Watch it on demand now.

A few months ago, I noticed something happening. I would spend all day working with LLMs—prompting them, reviewing their work, and correcting them—and when I wasn’t working on my own code, I was reviewing LLM-generated code. By the end of the day, I was exhausted. This was a very unusual thing for me: I’ve been a software developer at startups for 30 years, and while sometimes I might have gotten stressed out, I had never been exhausted by the actual act of writing code.