432 related articles

Codex is OpenAI's AI coding assistant that lets you write code using natural language. Learn its core features, use cases, and why programmers must master AI coding tools.

Codex is OpenAI's AI programming assistant that lets you write code in natural language. This article breaks down Codex's core features, use cases, and why programmers must master AI coding tools.

A new solo-company paradigm: replace human staff with AI Agent teams to fully automate newsletter research, writing, publishing, and analytics. 27,000 subscribers, monthly cost slashed from $1,500 to $19.

Anthropic's Applied AI team breaks down a methodology for choosing AI models: building custom evals, avoiding three common pitfalls, measuring value by cost per success, and cutting costs with prompt caching and context engineering.

A new one-person company model: replacing human staff with an AI Agent team to fully automate newsletter research, writing, publishing, and analytics. 27,000 subscribers, monthly cost cut from $1,500 to $19.

Ponytail, GitHub's #1 monthly open-source Skill, injects a 'less is more' engineering philosophy into AI Agents, cutting code volume by 54% on average. Compatible with 20+ Agents like Claude Code and Cursor.

Ponytail, GitHub's #1 monthly open-source Skill, injects a 'less is more' philosophy into AI Agents, cutting code volume by an average of 54%. Compatible with 20+ Agents including Claude Code, Cursor, and Copilot.

DeepSeek founder Liang Wenfeng reveals a five-step AGI roadmap from chain-of-thought to embodied intelligence. How does TileLang crack domestic GPU substitution under a 20,000-card constraint?

DeepSeek founder Liang Wenfeng reveals a five-step AGI roadmap—from chain-of-thought to embodied intelligence—under a 20,000-GPU constraint, using the TileLang compiler to break domestic substitution challenges while API cash flow backs AGI exploration.

DeepSeek open-sources DeepSpec, a full-stack speculative decoding library delivering 60–85% inference speedup and up to 661% throughput gains in production. MIT license, 9 checkpoints, 9 benchmarks.

Kimi, Alibaba Qwen, and DeepSeek leverage MoE architecture, home-field data advantages, and the open-source flywheel to close in on OpenAI and Anthropic at ultra-low cost. A deep dive into China's open-source LLM catch-up.

DeepSeek founder Liang Wenfeng systematically explains: a KPI-free culture, 10-month break-even pricing, long-term open-source strategy, continual learning to break the AGI bottleneck, and his prediction of a mature domestic chip ecosystem within a year.

In-depth analysis of the five core dimensions of AI Agent testing: command safety, tool-calling accuracy, task planning, output consistency, and error self-repair. Master automated testing and the transition path for test engineers.

An in-depth analysis of the five core dimensions of AI Agent testing: command safety, tool-calling accuracy, task planning, output consistency, and error self-repair. Master automated testing methods and the transition path for test engineers.

OpenAI GPT-5.6 launches Sol, Terra, and Luna simultaneously. We compare benchmarks and real-world coding tests to help you choose the right model for your needs.

Context engineering is the core methodology for building efficient AI Agents, covering query enhancement, RAG retrieval, prompt design, memory management, and tool invocation. Master Write, Select, Compress, and Isolate to solve LLM hallucination at its root.
Human-Centered AI: Real-World Implemen…
An MSR workshop reveals the truth about AI deployment: from a $20 corneal diagnostic device to expert-in-the-loop chatbots, researchers share real-world experiences of AI in healthcare and design within resource-scarce environments.

T-Head open-sources AI software stack T-Head SAIL at WAIC to lower the barrier for domestic chip development; Kimi K3 tops the WebDev leaderboard; Qwen 3.8 Max Preview cuts prices aggressively; Moonshot prepares a Hong Kong IPO; and Oracle switches its data center to a fuel cell microgrid.

Opus 5 moving to API billing? 5 proven tips to cut token costs by up to 80%: lower Effort Level, architect-executor split, Ponytail compression, Deep Research, and Advisor Mode — while outperforming Opus 4.8.

Anthropic engineers reveal Claude Code's 18-month evolution: system prompt cut by 80%, 65% of PRs shipped automatically by AI, Claude Tag collaboration, and the safety logic behind auto mode.