AWS Machine Learning Blog发布于 09/17 03:00

Improving HCLS AI reasoning with open-source agent skills

(翻译)使用开源 Agent 技能改进 HCLS AI 推理

AI agents on foundation models often misapply healthcare and life sciences decision frameworks, citing the right guideline but applying it incorrectly. This post shares 38 open-source agent skills across 11 HCLS domains that close this gap, with installation steps, three worked use cases, and a 410-

查看原文
AWS Machine Learning Blog发布于 09/17 02:59

Fault tolerant distributed training on Amazon EKS using NVRx

(翻译)使用 NVRx 在 Amazon EKS 上进行容错分布式训练

Integrate NVIDIA Resiliency Extension (NVRx) into PyTorch FSDP training on Amazon EKS to overlap checkpoint I/O with training and recover from GPU faults in seconds. This post covers async checkpointing, in-process restart, and ft_launcher in-job restart, with H100 benchmarks at 2 to 8 nodes showing

查看原文
NVIDIA Technical Blog发布于 09/17 00:28

Translating CUDA Tile Operations from Python to Rust Using Agentic AI

(翻译)使用 Agentic AI 将 CUDA Tile 操作从 Python 翻译为 Rust

cuTile Rust () is a tile-based system for safe, idiomatic GPU kernel authoring in the Rust programming language. Extending the Rust ownership model to tile…

查看原文
Solidot发布于 09/16 23:54

PS2 Fat 使用的安全芯片在时隔 26 年被破解

Solidot是至顶网的科技资讯网站,主要面对开源自由软件和关心科技资讯读者群,包括众多中国开源软件的开发者,爱好者和布道者。口号是“奇客的知识,重要的东西”。

查看原文
AWS Machine Learning Blog发布于 09/16 23:47

Optimizing agent system prompts with Amazon Bedrock AgentCore

(翻译)使用 Amazon Bedrock AgentCore 优化智能体系统提示词

AgentCore optimization turns production traces into proposed configuration changes, then validates them before promotion. This technical companion to the launch post explains how the system prompt optimizer's reflector engine works and shares benchmark results for the Single Agent and Sub-Agent Refl

查看原文
Solidot发布于 09/16 23:27

Denuvo 起诉黑客违反 DMCA 反规避条款

Solidot是至顶网的科技资讯网站,主要面对开源自由软件和关心科技资讯读者群,包括众多中国开源软件的开发者,爱好者和布道者。口号是“奇客的知识,重要的东西”。

查看原文
AWS Machine Learning Blog发布于 09/16 23:17

Build a serverless PII redaction pipeline with Amazon Bedrock Data Automation

(翻译)使用 Amazon Bedrock Data Automation 构建无服务器 PII 脱敏流水线

Learn how to automate end-to-end PII detection and redaction from scanned documents at scale using Amazon Bedrock Data Automation with a custom blueprint, AWS Step Functions, and AWS Lambda. A custom blueprint redacts sensitive fields with field-level precision, and a token matching quality check ra

查看原文