首页 话题 library logo 文库 码库 小摊
更多
所有 › 分类：技术 × › 语言：英文 ×
分类
商业 产品 技术 方法 科普
语言
中文 英文 日文 韩文

A Human-Augmenting Agentic Workflow for Causal Inference

netflix技术
译 技术 xiaozi 于 2026-06-26 投稿

Hybrid Core Allocation: From Overallocation to Reliable Sharing

uber技术
译 技术 xiaozi 于 2026-05-03 投稿

How to finally trust Claude's advice (using Karpathy's LLM Council method)

译 技术 菜涂涂 于 2026-03-31 投稿

Defining Continual Learning

译 技术 xiaozi 于 2026-04-23 投稿

The Anatomy of an Agent Harness

译 技术 xiaozi 于 2026-04-07 投稿

Our evaluation of Claude Mythos Preview’ s cyber capabilities

译 技术 xiaozi 于 2026-04-14 投稿

You Don't Know LLM Training: Principles, Pipelines, and New Practices

译 技术 xiaozi 于 2026-04-10 投稿

Harness Engineering: Why the Best AI Engineers in 2026 Stopped Writing Code

译 技术 xiaozi 于 2026-03-28 投稿

From Silos to Service Topology: Why Netflix Built a Real-Time Service Map

netflix技术
译 技术 蓝伤耀雪 于 2026-06-26 投稿

Palana (Part 2): Architecting isolation, identity, and auditability for AI agents

grab技术
译 技术 xiaozi 于 2026-06-26 投稿

What's an Agent Harness? And how do I choose the best one?

译 技术 冯广鑫 于 2026-04-11 投稿

Perfecting Baseline

译 技术 小小砍地 于 2025-11-15 投稿

Achieving Near-Linear Training Scalability for Pinterest’ s Foundation Models

pinterest技术
译 技术 xiaozi 于 2026-06-26 投稿

Understanding LLMs from Scratch Using Middle School Math

译 技术 xiaozi 于 2026-04-10 投稿

Better Harness: A Recipe for Harness Hill-Climbing with Evals

译 技术 xiaozi 于 2026-04-10 投稿

首页 - Wiki
Copyright © 2011-2026 iteam. Current version is 2.155.2. UTC+08:00, 2026-06-29 06:44
浙ICP备14020137号-1 $访客地图$