2+ week, 6+ day ago   (814+ words) Agentic sessions are characterized by multiturn inference. At the end of each turn, the agent’s output is appended to the continually growing context that is fed into all subsequent turns. As Figure 1 shows, context can grow to hundreds of thousands…...

2+ week, 6+ day ago   (205+ words) North-south networks provide the access path into and out of a data center, connecting users, applications, data sources, storage systems, and services to individual systems. Traditional cloud data centers built these networks around software-defined infrastructure, composability, and elasticity, so resources…...

2+ week, 6+ day ago   (443+ words) AgentX is the agentic-coding benchmark in InferenceX, SemiAnalysis’s open-source benchmark suite. It measures how efficiently accelerators serve the request patterns produced by real coding agents. Agentic sessions are long, stateful, and variable: they chain model calls, tool use, and growing…...

3+ week, 1+ day ago   (289+ words) The shape of an agentic trajectory is defined by its length and width (Figure 2). This is why the relevant optimization target for an agentic CPU fleet is the total number of completed user sessions, not raw core count. High-core-count systems…...

3+ week, 2+ day ago   (1011+ words) The research project elevates Claude Opus 5 from a 30% model baseline to 100% as part of the complete AVO agent system, showing that system design—not model capability alone—can unlock frontier-level long-horizon performance This post introduces the AVO architecture and the…...