The Agent Harness Is Getting Out of Control
The model is only one part of an AI agent. The harness around it is becoming the real system.
machine-learning
4 posts
The Curious Case of Agent Memory
Approaches agents use to manage context: compaction, external retrieval, and learned experience.
LLM Serving and the Bus That Never Stops
In-flight batching is the trick that keeps LLM serving from wasting GPU seats.
Word Embedding is Magic!
Word embedding is a magic trick that allows computers to understand language.