今日已更新 184 条资讯 | 累计 37433 条内容
关于我们

标签:#trans

找到 425 篇相关文章

AI 资讯

Presentation: Enhancing Reliability Using Service-Level Prioritized Load Shedding at Netflix

The speakers discuss Netflix’s architecture for surviving extreme traffic spikes. They explain the mechanics of prioritized load shedding embedded in their Envoy sidecar proxy, allowing user-initiated requests to steal capacity from non-critical traffic. They share automated platform strategies for continuous chaos load testing, config generation, and retry storm mitigation. By Anirudh Mendiratta, Benjamin Fedorka

2026-07-02 原文 →
AI 资讯

Presentation: Graph RAG: Building Smarter Retrieval Workflows with Knowledge Graphs

Cassie Shum discusses the architectural evolution of GraphRAG and why data foundations are critical for advanced AI workflows. She explains how traditional vector RAG falls short when addressing global context, multi-hop reasoning, and provenance. She shares enterprise strategies for building semantically structured knowledge graphs that shift raw orchestrating logic down to the data layer. By Cassie Shum

2026-07-01 原文 →
AI 资讯

Presentation: The Infrastructure Challenge Behind Production AI

The panelists explain the realities of running AI systems reliably at scale. While building models is solved, maintaining production databases under constant pressure is not. They discuss the emerging architectural decisions separating teams that scale gracefully from those facing catastrophic outages, and what engineering leaders must rethink today. By Simerus Mahesh, Alex Infanzon, Meryem Arik, Luca Bianchi, Renato Losio

2026-07-01 原文 →
AI 资讯

Presentation: Trustworthy Productivity: Securing AI-Accelerated Development

Sriram Madapusi Vasudevan discusses industry-converging patterns for securing autonomous AI agents in production. He explains the critical vulnerabilities hidden inside the ReAct loop across context, reasoning, and tool execution. He shares how to mitigate risks like memory poisoning and rogue tool execution using defense-in-depth strategies, LLM-as-a-judge critics, and MAESTRO threat modeling. By Sriram Madapusi Vasudevan

2026-06-30 原文 →
AI 资讯

This motor could be the future of e-bikes

Imagine an e-bike motor that lets you select your preferred pedaling cadence and then automatically adjusts the gears to keep your legs spinning at that exact speed, no matter how steep the hill gets - all without a fragile derailleur or heavy multi-speed cassette to maintain. Prefer manual control? No problem, you can have as […]

2026-06-30 原文 →
AI 资讯

Presentation: Million PDFs: Building a Modern Document Infrastructure with Rust and Typst

Erik Steiger discusses the operational pain of legacy PDF generation in regulated banking and manufacturing. He explains how transitioning from resource-heavy engines like Puppeteer and LaTeX to a serverless Rust architecture powered by Typst can drop render latencies below 2ms. He shares how applying Git and Docker concepts to template registries ensures ironclad compliance and rapid debugging. By Erik Steiger

2026-06-29 原文 →