Follow us to discover more Baidu tech insights.
This article introduces an eight‑dimensional, weighted scoring system for evaluating AI Skills, explains each metric, demonstrates the framework on real‑world Skills, compares similar Skills, and shows how multi‑model cross‑validation and four execution strategies improve assessment reliability.
This article details how Karpathy's AutoResearch methodology was transferred to software development, introducing multi‑agent cross‑review, a five‑dimensional quantitative scoring system, and feedback‑driven iteration to build a fully automatic pipeline that resolves a medium‑complexity GitHub Issue in about ten minutes with a 9.0/10 code‑quality score.
This article dissects the leaked Claude Code v2.1.88 source to reveal how the three core concepts—Rules, MCP, and Skills—are implemented, where they are injected in the Anthropic LLM API request, and when developers should prefer each mechanism for reliable, secure, and token‑efficient coding agent workflows.
Baidu Cloud’s 7th‑generation AI confidential virtual machine combines Intel TDX‑based CPU trusted execution, GPU confidential computing, and DPU‑offloaded I/O to provide end‑to‑end encrypted data paths, multi‑GPU scaling, and near‑native performance for high‑sensitivity AI workloads, redefining secure cloud AI infrastructure.
This article analyzes the challenges of using AI coding agents for large‑scale, long‑running tasks such as bulk file migration or code review, and presents a systematic engineering approach—including task decomposition, parallel execution, persistent progress files, resumable workflows, and multi‑level retry strategies—backed by concrete script examples and real‑world case studies.
IMClaw is an open‑source AI‑Agent gateway that implements the ACP (Agent Client Protocol) to let developers control Claude, Codex, Gemini and dozens of other agents from IM tools or remote servers, offering session management, permission control, and a lightweight CLI called acpx.
An in‑depth guide walks you through installing OpenClaw, understanding its gateway, channel, agent, tool, and skill architecture, managing token costs, creating multi‑agent workflows, securing API keys, and troubleshooting common issues, empowering developers to build scalable AI‑driven automation.
This article analyzes the challenges of scaling ClickHouse within Baidu’s MEG data platform and details a lake‑house solution that decouples storage and compute, integrates a meta‑service for transparent data access, optimizes query performance through caching, data roll‑up and layout tuning, and introduces a unified query gateway that gracefully falls back to Spark for complex workloads.
This article explains why large‑model agents need structured Skills to capture team‑specific knowledge and workflows, describes the evolution from MCP to Skill, details the progressive‑disclosure design, shows how to write, organize, and install Skills, and provides a systematic evaluation and iteration process to ensure high‑quality, token‑efficient agent behavior.
This article recounts how Baidu's storage team tackled the performance and scalability limits of traditional object storage by redesigning metadata handling with the Mantle and MantleX architectures, introducing a centralized IndexNode, strong consistency, delta‑record writes, and a seamless single‑node to distributed transition for massive file systems.
