Author

Tencent Technical Engineering

Official account of Tencent Technology. A platform for publishing and analyzing Tencent's technological innovations and cutting-edge developments.

130

Articles

Likes

1.3k

Views

Comments

Latest from Tencent Technical Engineering

100 recent articles max

Tencent Technical Engineering

Oct 13, 2026 · Artificial Intelligence

How LLMs Work: From Next-Token Prediction to Intelligence

This comprehensive guide explains large language models from first principles, covering token prediction, information theory, neural networks, Transformer architecture, training via gradient descent, and the path from base models to chat assistants like ChatGPT, including limitations such as hallucinations.

Attention MechanismBackpropagationGradient Descent

0 likes · 74 min read

How LLMs Work: From Next-Token Prediction to Intelligence

Tencent Technical Engineering

Oct 12, 2026 · Backend Development

Agent, MCP, Skill, CLI, Model: Concept Map & Three Paths for Legacy AI Integration

This article maps the relationships among Agent, MCP, Skill, CLI, and Model using a team analogy, details a full tool-call relay, and presents three prioritized integration paths — API wrapping, CLI wrapping, and RPA fallback — for connecting AI to legacy enterprise systems, with real automotive case studies.

API wrapperAgentCLI

0 likes · 13 min read

Agent, MCP, Skill, CLI, Model: Concept Map & Three Paths for Legacy AI Integration

Tencent Technical Engineering

Oct 9, 2026 · R&D Management

Beyond AI Coding: End-to-End AI Automation Reshapes R&D Pipelines

The article details OK Platform's AI-driven end-to-end R&D pipeline that automates nine stages from requirement to deployment, achieving 68% auto-completion and 51% within 2 hours, using zero-based thinking to eliminate human bottlenecks, with structured specs, quality gates, knowledge flywheel, and human-as-decision-maker model.

AI-driven R&DOK PlatformOrganizational Efficiency

0 likes · 48 min read

Beyond AI Coding: End-to-End AI Automation Reshapes R&D Pipelines

Tencent Technical Engineering

Sep 23, 2026 · Operations

How an AI Agent Cuts Error Code Triage from Hours to Minutes: Three Practices

This article details how an AI Agent on an orchestration platform automates error code root cause analysis by integrating knowledge bases, code graphs, observability data, and code hosting platforms, achieving 88% consistency with human annotations and zero hard conflicts across 50 test cases through a five-step investigation workflow, dual-path JSON parsing, and regression-tested prompt optimization.

AI AgentError Code TroubleshootingObservability

0 likes · 26 min read

How an AI Agent Cuts Error Code Triage from Hours to Minutes: Three Practices

Tencent Technical Engineering

Sep 22, 2026 · Backend Development

Tencent Backend Veteran's Reset: Mastering LLM Inference Engineering from Zero

A Tencent senior backend engineer with 15 years experience shares his transition to LLM inference engineering, detailing learning paths for model architecture, inference optimization, and self-assessment exercises, while arguing that traditional infrastructure skills remain crucial for AI Infra and Agent Infra development.

AI infrastructureBackend EngineeringKV cache

0 likes · 38 min read

Tencent Backend Veteran's Reset: Mastering LLM Inference Engineering from Zero

Tencent Technical Engineering

Sep 21, 2026 · Artificial Intelligence

Jev Engineering: Moving Judgment Tasks Out of LLMs for Faster AI Agents

This article explores Jev (System One Model) as a specialized probability judgment layer for AI agents, detailing its three primitives (Choice, Score, Noul), the fast-jev-compaction project for context pruning, and a demo implementation showing 91.5% context reduction while preserving critical debugging details like file paths and error codes.

AI AgentsJevLLM Engineering

0 likes · 32 min read

Jev Engineering: Moving Judgment Tasks Out of LLMs for Faster AI Agents

Tencent Technical Engineering

Aug 31, 2026 · Cloud Native

CubeSandbox v0.7.0: Cross-Machine Sandbox Migration & Multi-Version Runtime Support

CubeSandbox v0.7.0 introduces cross-machine pause/resume via S3 backend storage, allows component multi-version coexistence so upgrades don't break existing templates, merges NetworkAgent into Cubelet to cut RPC calls and speed cold starts, and separates control-plane scheduling from node operations via new CubeOps service.

Cloud NativeCubeSandboxKubernetes

0 likes · 10 min read

CubeSandbox v0.7.0: Cross-Machine Sandbox Migration & Multi-Version Runtime Support

Tencent Technical Engineering

Aug 28, 2026 · Artificial Intelligence

Tencent Hunyuan Hy4 Preview: 770B Open-Source Model Claims Top Tier

Tencent releases Hunyuan Hy4 preview, a 770B parameter mixture-of-experts model with 49B activated parameters and 1M context length, achieving top-tier open-source performance across coding, office, gaming, and scientific tasks, with internal blind tests showing 2.99/4 score surpassing GLM 5.3 and Kimi K3, plus 31.8% inference throughput gains via self-optimization.

HunyuanHy4LLM

0 likes · 6 min read

Tencent Hunyuan Hy4 Preview: 770B Open-Source Model Claims Top Tier

Tencent Technical Engineering

Aug 27, 2026 · Artificial Intelligence

AI Coding Deep Dive: Why Humans Must Retreat to Judgment, Not Code Review

This 20k-word article shares production lessons from building AI coding agents: prompts hit diminishing returns so constraints must move into frameworks; orchestration requires runtime sovereignty; evaluation needs executable criteria like mutation kill rates; humans shift from code review to judgment gates; and nested verification loops replace trust with verifiable facts.

AI Coding Agentsagent orchestrationevaluation frameworks

0 likes · 77 min read

AI Coding Deep Dive: Why Humans Must Retreat to Judgment, Not Code Review

Tencent Technical Engineering

Aug 20, 2026 · Big Data

Tencent SuperSQL Sets New TPC‑DS World Record, Leads in Performance and Cost Efficiency

Tencent's SuperSQL achieved a 654 million composite score on the TPC‑DS 100 TB benchmark—nearly ten times the previous record—while cutting performance‑per‑dollar cost to 11.04 CNY (about one‑sixth of earlier results), thanks to innovations in query optimization, a vectorized execution engine, adaptive memory and shuffle mechanisms, and AI‑driven diagnostics that together deliver superior speed, scalability, and business value.

AI diagnosticsDistributed ComputingQuery Optimization

0 likes · 18 min read

Tencent SuperSQL Sets New TPC‑DS World Record, Leads in Performance and Cost Efficiency