Next week at KubeCon + CloudNativeCon, the teams running AI workloads and large-scale platform engineering in production will share what actually works and what breaks.
If you want real operational takeaways in person, register today: bit.ly/4hwqfuN
- Before evaluating a dedicated AI SRE, start with the agent you already have. Roy Libman shows that pairing existing models with read-only cluster timelines resolves 86% of Kubernetes faults in under two minutes, dropping average diagnosis time from 191s to 64s. Read more:
- One model per GPU leaves expensive capacity on the table. Join Weiqi Sun of @nvidia at #KubeCon + #CloudNativeCon North America to explore agent-driven model placement for better GPU utilization on Kubernetes. 📅 November 9-12 📍 Salt Lake City Register:
- Networking, with a plot twist. 🧩 Explore Sponsor-hosted Co-located Events alongside #KubeCon + #CloudNativeCon North America, November 9-12 in Salt Lake City. Separate registration required: bit.ly/4rYVxiO Register for the main event: bit.ly/3BDI5XL
- Today is your last chance to save on #gRPConf India 🚨 Prices go up tomorrow, 29 October. Register now for a full day in Bengaluru packed with gRPC talks, demos, and hands-on labs with the developers and architects shaping the ecosystem. 🎟️ Register: bit.ly/4beWDzR


