分类浏览
按技术领域分类浏览全部文章
总览
排行榜
分类浏览
文章关系图
GitHub 映射
C1: Agent 开发
10 篇
Building Effective AI Agents
2024-12-19 | agent-architecture
agent
workflow
orchestration
8.8
A
How We Built Multi-Agent Research System
2025-06-13 | multi-agent
multi-agent
research
parallelization
8.2
A
Scaling Managed Agents
2026-04-08 | agent-architecture
managed-agents
decoupling
7.7
B
Equipping Agents with Agent Skills
2025-10-16 | agent-skills
agent-skills
procedural-knowledge
7.6
B
Harness Design for Long-Running Apps
2026-03-24 | agent-harness
harness
long-running
7.4
B
Building a C Compiler with Parallel Claudes
2026-02-05 | multi-agent
multi-agent
fan-out
7.3
B
Effective Harnesses for Long-Running Agents
2025-11-26 | agent-harness
harness
compaction
7.3
B
Demystifying Evals for AI Agents
2026-01-09 | agent-eval
eval
benchmark
7.2
B
SWE-bench Verified
2025-01-06 | agent-eval
SWE-bench
benchmark
6.6
C
Quantifying Infrastructure Noise
2026-02-05 | agent-eval
eval
infrastructure
6.7
C
C2: 工程实践
6 篇
Effective Context Engineering for AI Agents
2025-09-29 | context-engineering
context
compaction
memory
9.0
S
Introducing Contextual Retrieval
2024-09-19 | context-engineering
RAG
embedding
8.9
S
Writing Effective Tools for Agents
2025-09-11 | tool-design
MCP
tool-design
ACI
8.7
A
Claude Code: Best Practices
2025-04-18 | coding-best-practices
CLAUDE.md
agentic-coding
8.3
A
The "Think" Tool
2025-03-20 | prompt-engineering
think-tool
reasoning
8.3
A
AI-Resistant Technical Evaluations
2026-01-21 | coding-best-practices
eval
interview
6.6
C
C4: 工具与平台
6 篇
Introducing Advanced Tool Use
2025-11-24 | sdk
tool-search
programmatic
8.9
S
Desktop Extensions: One-Click MCP
2025-06-26 | mcp
MCP
MCPB
8.0
A
Beyond Permission Prompts (Sandboxing)
2025-10-20 | claude-code
sandboxing
security
8.0
A
Code Execution with MCP
2025-11-04 | mcp
MCP
code-execution
7.9
A
Claude Code Auto Mode
2026-03-25 | claude-code
auto-mode
permissions
6.9
C
Claude Code Quality Update
2026-05-01 | claude-code
quality
bug-fix
4.7
D
C3: 模型研究
9 篇
Teaching Claude Why
2026-05-08 | alignment
alignment
safety
7.5
B
Automated Alignment Researchers
2026-04-14 | alignment
alignment
automated
7.1
B
Natural Language Autoencoders
2026-05-07 | interpretability
interpretability
transparency
7.0
B
What 81,000 People Want from AI
2026-03-18 | societal-impacts
survey
user-research
6.7
C
BioMysteryBench
2026-04-29 | science
science
bioinformatics
6.6
C
Donating Alignment Tool
2026-05-07 | alignment
alignment
open-source
6.4
C
Project Deal
2026-04-24 | societal-impacts
negotiation
experiment
5.9
C
Personal Guidance
2026-04-30 | societal-impacts
user-behavior
5.5
C
Project Vend: Phase Two
2025-12-18 | societal-impacts
autonomous
experiment
5.1
C
C5: 安全与政策
4 篇
What 81K People: Economics of AI
2026-04-22 | economic-research
5.7
C
Economic Index Survey
2026-04-22 | economic-research
5.1
C
2028: Two Scenarios
2026-05-14 | policy
5.1
C
Institute Focus Areas
2026-05-07 | policy
3.9
D