
It answers the standing question of how to let untrusted AI-generated code run in a real product, with a architecture specific enough to copy.
“My, uh, key point is personal AI codegen breaks traditional cloud infrastructure.”
Kenton Varda
“On the web, everyone can build whatever they want. And it turns out it's fine. It's not the security disaster that Apple and Google keep telling us would happen.”
Kenton Varda
“it's almost like easier to in the United States to buy a gun than it is to like get access to your own phone to install unsigned software”
Kenton Varda
“there is no security bug you can have in this code that matters”
Kenton Varda
“Kenton I don't think you should yeet this. I don't think this is yeet material.”
Kenton Varda
videoOperating Distributed Inference Systems at Scale — Nishant Gupta & Naman Ahuja, Meta
videoVertical Mobility: Inference from MVP to Trillion-Parameter Workloads — Sitanshu Gupta, CoreWeave
videoAre LLM Performance Benchmarks Reliable? — Ashok Chandrasekar & Jason Kramberger, Google
videoRouting LLM Inference in Production: From Engine Signals to Policy — Qianru Lao & Lu Zhang, OpenAIChecking sign-in…
Loading comments…