BestHub
Sign in
Baidu Geek Talk
Author

Baidu Geek Talk

Follow us to discover more Baidu tech insights.

520
Articles
0
Likes
1.6k
Views
0
Comments
Recent Articles

Latest from Baidu Geek Talk

100 recent articles max
Baidu Geek Talk
Baidu Geek Talk
Jun 10, 2026 · Artificial Intelligence

Accelerating Feature Delivery: Harness AI‑Driven Development Cuts One‑Day Work to Two Hours

The article details how a team upgraded from Vibe Coding to a Harness workflow—restructuring the codebase into a single monorepo with Git submodules, defining six specialized Sub‑Agents, implementing an Agent Handoff protocol, and automating the entire requirement‑to‑test pipeline, achieving a four‑fold speedup (one day to roughly two hours) while slashing front‑end/back‑end coordination overhead.

AI AgentsContinuous IntegrationSoftware Automation
0 likes · 23 min read
Accelerating Feature Delivery: Harness AI‑Driven Development Cuts One‑Day Work to Two Hours
Baidu Geek Talk
Baidu Geek Talk
Jun 1, 2026 · Cloud Computing

Cut Migration Time by 60%: How Baidu Cloud Scaled Intel Xeon 6 QAT‑Accelerated VM Live Migration

VM live migration in large cloud clusters suffers from high CPU load and long downtime; Baidu Cloud integrated Intel Xeon 6 processors with built‑in QuickAssist Technology to offload memory compression, achieving up to 60% reduction in migration duration, 20% lower CPU usage, and sub‑10 ms pause windows.

CPU offloadCloud ComputingIntel QAT
0 likes · 10 min read
Cut Migration Time by 60%: How Baidu Cloud Scaled Intel Xeon 6 QAT‑Accelerated VM Live Migration
Baidu Geek Talk
Baidu Geek Talk
Jun 1, 2026 · Artificial Intelligence

When CPUs Hide GPU Bottlenecks: How Btune 2.0’s Automated Latency Analysis Breaks the Performance Black Box

The article examines how hidden CPU‑GPU coordination issues can cripple AI inference performance, illustrates a real‑world XPU migration case where a kernel lock in the halolet component throttled throughput, and shows how Btune 2.0’s automated latency analysis and AI agent automatically pinpoint and resolve such bottlenecks.

AI performanceBtune 2.0CPU-GPU bottleneck
0 likes · 10 min read
When CPUs Hide GPU Bottlenecks: How Btune 2.0’s Automated Latency Analysis Breaks the Performance Black Box
Baidu Geek Talk
Baidu Geek Talk
May 25, 2026 · Artificial Intelligence

RenderFlow: Agentic Code Delivery for Baidu’s Vertical Search Rendering Service

The article presents RenderFlow, a system that integrates LLM‑generated code into Baidu’s search result rendering pipeline by building a generate‑execute‑feedback‑repair‑publish loop, detailing its architecture, multi‑round repair mechanism, quality safeguards, and the resulting reduction of delivery cycles from days to minutes across nearly a thousand scenarios.

LLMagentic deliverycode generation
0 likes · 23 min read
RenderFlow: Agentic Code Delivery for Baidu’s Vertical Search Rendering Service
Baidu Geek Talk
Baidu Geek Talk
May 25, 2026 · Artificial Intelligence

Accelerating Multimodal Model Training: LoongForge's DP Load‑Balancing Optimization Explained

The article analyzes how data‑parallel (DP) load imbalance hampers large‑scale multimodal model training, details LoongForge's two‑stage adaptive data‑reallocation method that builds a precise compute‑cost model and dynamically redistributes samples, and presents experimental results showing up to 10% throughput gains on massive DP clusters.

DP load balancingData ParallelDistributed Training
0 likes · 16 min read
Accelerating Multimodal Model Training: LoongForge's DP Load‑Balancing Optimization Explained
Baidu Geek Talk
Baidu Geek Talk
May 20, 2026 · Artificial Intelligence

How We Tamed AI Output with a Three‑Layer Architecture for Android Code Migration to KMP

This article details how we used a three‑layer AI architecture—Skill for stable execution, SubAgent for context‑aware scheduling, and Agent Team for parallel collaboration—to reliably migrate a large Android codebase to a Kotlin Multiplatform project, addressing instability, context inflation, and efficiency challenges.

AIAgent TeamAndroid
0 likes · 15 min read
How We Tamed AI Output with a Three‑Layer Architecture for Android Code Migration to KMP
Baidu Geek Talk
Baidu Geek Talk
May 18, 2026 · R&D Management

Automating the Full Development Cycle with Claude Code’s /prd, /goal, and /after-goal

Using a real-world case, the article demonstrates how Claude Code’s three slash commands—/prd, /goal, and /after-goal—can fully automate a development workflow, turning requirement decomposition into structured PRDs, card‑based implementation, and automatic code submission, review, and closure, thereby boosting efficiency and consistency.

AI automationCI/CDCLI
0 likes · 14 min read
Automating the Full Development Cycle with Claude Code’s /prd, /goal, and /after-goal
Baidu Geek Talk
Baidu Geek Talk
May 13, 2026 · Artificial Intelligence

LoongForge Boosts Multimodal Training Speed by 45% on GPU and Kunlun XPU

LoongForge, Baidu Baige’s open‑source full‑modal training framework, unifies LLM, VLM and VLA workloads, runs unchanged on NVIDIA GPUs and Kunlun XPU, and delivers 15‑45% end‑to‑end speedups with up to 90% linear scaling on 5,000‑plus card clusters, while simplifying model integration via YAML.

AI InfrastructureGPUKunlun XPU
0 likes · 23 min read
LoongForge Boosts Multimodal Training Speed by 45% on GPU and Kunlun XPU
Baidu Geek Talk
Baidu Geek Talk
May 13, 2026 · Frontend Development

Enabling Agents to See the Browser: A Runtime Harness Using Chrome DevTools Protocol

The article explains why AI agents need to perceive actual browser rendering, introduces an open‑source Browser Use skill built on Chrome DevTools Protocol that lets agents verify path, content, visual layout, interaction, console and network dimensions, and details the setup, workflow, optimization tips and practical deployment schemes.

AI AgentBrowser automationChrome DevTools Protocol
0 likes · 25 min read
Enabling Agents to See the Browser: A Runtime Harness Using Chrome DevTools Protocol
Baidu Geek Talk
Baidu Geek Talk
Apr 22, 2026 · Artificial Intelligence

How to Quantify AI Skill Quality with an 8‑Dimension Evaluation Framework

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.

AI skill evaluationFrameworkMetadata Quality
0 likes · 15 min read
How to Quantify AI Skill Quality with an 8‑Dimension Evaluation Framework