I love the new Google AI pro limits for Antigravity. Just 2 hours of working with a very small codebase and Im done for a week. Do not like the future we are heading into.
Recursive Language Models (RLMs) let agents manage 10M+ tokens by delegating tasks recursively.
This Google Cloud Community Article explains why ADK was the perfect choice for re-implementing the original RLM codebase in a more enterprise-ready format →https://t.co/p3MsNtLVJL
Linus is looking at the crowd, thinking how fast he can leave the venue. Asked for a selfie, but he politely declined while a guy from the conference (organiser?) with a fear in his eyes told me whispering "they will kill me if I allow you to take a photo". :(
Scaling stateful game servers on K8s is usually a nightmare.
Just saw the #Agones demo at #OSSummit.
Core concept: Game Server = K8s Pod. 🤯
It handles the fleet scaling and binpacking across clusters automatically.
Smart abstraction for high-velocity stateful workloads.
100% agree. We are not in an AI bubble but in a LLM bubble. Pretty soon we will see only one or two OS LLMs that will be the same thing as K8s right now is for you infrastructure. #OSSummit#AIDev