Only 50% of companies monitor their ML systems. Building observability for AI is not simple: it goes beyond 200 OK pings. In this episode, Sylvain Kalache sits down with Conor Brondsdon (Galileo) to unpack why observability, monitoring, and human feedback are the missing links to make large language model (LLM) reliable in production. Conor dives into the shift from traditional test-driven development to evaluation-driven development, where metrics like context adherence, completeness, and ac...
All content for Humans of Reliability is the property of Rootly and is served directly from their servers
with no modification, redirects, or rehosting. The podcast is not affiliated with or endorsed by Podjoint in any way.
Only 50% of companies monitor their ML systems. Building observability for AI is not simple: it goes beyond 200 OK pings. In this episode, Sylvain Kalache sits down with Conor Brondsdon (Galileo) to unpack why observability, monitoring, and human feedback are the missing links to make large language model (LLM) reliable in production. Conor dives into the shift from traditional test-driven development to evaluation-driven development, where metrics like context adherence, completeness, and ac...
Are AI and Platforms Making SRE Obsolete? With Kaspar von Grünberg, Humanitec’s CEO
Humans of Reliability
25 minutes
7 months ago
Are AI and Platforms Making SRE Obsolete? With Kaspar von Grünberg, Humanitec’s CEO
Last year, over 89% of companies claimed to have adopted platform engineering. And, in the past month, LLMs have been disrupting how we think about software development. In this context, Kaspar, asks if the role of Site Reliability Engineers is being obsolete as we know it. Kaspar argues that while SREs aren’t going anywhere, their responsibilities are evolving—fast. We talk about: The need for the SRE role to be transformedHow to build reliability as part every golden pathThe role of AI and ...
Humans of Reliability
Only 50% of companies monitor their ML systems. Building observability for AI is not simple: it goes beyond 200 OK pings. In this episode, Sylvain Kalache sits down with Conor Brondsdon (Galileo) to unpack why observability, monitoring, and human feedback are the missing links to make large language model (LLM) reliable in production. Conor dives into the shift from traditional test-driven development to evaluation-driven development, where metrics like context adherence, completeness, and ac...
