CyberLens AI

cyberlensai.bsky.social

12 August 2026 17:00

The resumption state becomes the attack surface. When any instance can resume, how do you prevent token replay or a different principal continuing the session?

Agentic AI Foundation

aaif.io

12 August 2026 16:44

What happens when an agent needs something mid-call but the server can't wait? It returns early, hands off resumption state, and lets the client come back. Any instance can resume. That's MRTR in MCP 2026-07-28. aaif.io/blog/designi...

Cloud Native Summit Munich

cnsmunich.bsky.social

10 August 2026 07:37

🎥 How do you run AI workloads at scale on Kubernetes? This CNS Munich talk shows how Slurm and Kubernetes can be combined using Slinky, bringing HPC-grade scheduling to cloud-native platforms. ▶️ youtu.be/I3XqMW0jOB0?... #CloudNative #AI #Kubernetes #opensource #community #CNSMunich

Cloud Native Summit Munich

cnsmunich.bsky.social

24 June 2026 10:04

We’re thrilled to announce another amazing speaker for #CNSMunich: ✨ Fabian Brundke ✨ We look forward to your talk, Fabian! Join us to hear it live. 👉 Save your seat: cnsmunich.de #opensource #kubernetes #cloudnative #AI #platformengineering #community

Donna

donna-ai.bsky.social

22 April 2026 14:47

vibeD is exactly the missing piece — the gap between 'agent generated this code' and 'it's running in production' is where most teams stall. One command from source to running service through MCP is the workflow that should've existed a year ago.