90 posts on this topic
OpenAI plans to cut model access for Cursor, the AI code editor acquired by SpaceX. As tension between Sam Altman and Elon Musk escalates, Anthropic is increasing Claude support for Cursor.
Alibaba Cloud introduced the Qwen 3.8-Max model with 2.4 trillion parameters (95B active). With autonomous coding, self-improving systems running 10+ days, chip design and an open-source move, it sets a new bar for AI agents.
Anthropic has officially released Claude Opus 5, a new model that has stirred up the AI ecosystem. Offering Fable 5-level intelligence and reasoning at half the price, Opus 5 resets the standards for software development, cybersecurity analysis and agent-based workflows. Here are its pricing, performance benchmarks and standout features.
Steps for building a coding agent in Node.js and Python by using the Kimi API with OpenAI-compatible clients, plus MCP context and security notes.
How do DeepSeek's new open-source projects DSpark and DeepSpec speed up inference for V4 models by up to 85% without hurting quality?
GitHub Copilot's new 'Agent Mode' and terminal integration are kicking off the era of autonomous agents in software development. This review covers autonomous handling of multi-step tasks and MCP support.
Finding bugs from screenshots, fixing UI and reusable prompt patterns with Kimi vision prompting. A practical debugging guide.
If you want to use AI not just to chat but as a real assistant in your daily life and workflows, you need to know the right prompts. In this post I have collected the most effective Google Gemini prompt examples to boost your productivity.
Where Kimi K2.7 Code stands against Claude and GPT in coding benchmarks, the limits of these measurements and the practical takeaways for developers.
A practical, layer-by-layer 17-step roadmap guide to becoming an AI Engineer, from the very basics all the way to production.
Setting up an agentic coding flow in the terminal with Kimi Code CLI: defining tasks, the verification loop and tips for safe use.
The 'Instant Navigations' feature announced with the Next.js 16.3 preview release cuts the navigation delays of server components down to zero and gives apps an SPA-speed navigation experience.
Practices for generating HTML/CSS/React components from screenshots or Figma-style mockups with Kimi K2.5, plus limits and quality-control tips.
How does Kimi K2.7 Code stand out in long-context software tasks with token efficiency and multi-step engineering workflows? A practical assessment.
China's Z.AI has released its new open-source AI model GLM-5.2. Leading the Artificial Analysis Intelligence Index with 51 points, the model stands out with a 1 million token context window and leading performance on software engineering tests.
We look at the revolutionary 'Automation' feature that arrived with Cursor IDE's latest update and how multi-step autonomous AI agents manage writing code, debugging and testing.
Angular v22 promotes Signal Forms, Angular Aria and async reactivity to stable, simplifies dependency injection, improves templates and the router, makes OnPush the default and adds tooling for AI coding agents. A practical tour of what changes.
The developer-focused Windows features Microsoft announced at Build 2026: native Rust-based Coreutils for Windows, WSL container infrastructure, an Intelligent Terminal with ACP protocol support and Developer Configurations.
Anthropic's new model Claude Opus 4.8 is built on reliability and collaboration rather than raw speed. Effort control that lets users adjust processing depth, dynamic workflows that process hundreds of thousands of lines in parallel and a claim of four times fewer bugs in code stand out. I cover all the new features and the signals about the Mythos class.
In 2026, a good frontend stack shouldn't just offer fast development; it should also provide type safety, testability, observability and sustainable team practices. In this post I walk through the modern frontend tools I keep choosing for production projects.
According to financial projections Anthropic shared with investors, the company is preparing to report 10.9 billion dollars in revenue and about 559 million dollars in operating profit in the second quarter. Enterprise demand for Claude-based coding tools plays a decisive role in the company's growth, while a relative drop in compute costs strengthens the prospect of profitability.
Google announced Antigravity 2.0 at I/O 2026. The new release offers multi-agent orchestration, a native desktop app, a new CLI tool, voice control support and an SDK for building custom agents.
Google introduced Gemini 3.5 Flash at I/O 2026. The model outperforms 3.1 Pro in coding and agent tasks and became the default in the Gemini app and Google Search AI Mode. Parallel sub-agent support in Antigravity and Gemini Spark integration were also announced.
13 new CVEs disclosed across the Next.js and React ecosystem reopen the debate on framework architecture around RSC, middleware/proxy, WebSocket upgrades, cache poisoning and beforeInteractive script security.
In a podcast appearance, Anthropic CFO Krishna Rao said more than 90 percent of the company's code is now produced by Claude. The company's annualized revenue has grown from 9 billion dollars to more than 30 billion dollars, while Claude Code reached the 1 billion dollar revenue band in just six months.
OpenAI brought Codex support to the ChatGPT mobile app. iOS and Android users can now monitor and steer coding agents from their phones; macOS connections are supported today and Windows support is on the way.
According to Harvard professor David J. Malan, declining interest in computer science programs cannot be explained by generative AI alone. Slower hiring in the tech industry, fewer entry-level positions and uncertainty about career prospects are also changing the picture.
Node.js 26.0.0 Current is out. The Temporal API is now enabled by default, and V8 14.6 and Undici 8 updates await developers.
Claude Code's Repeatable Routines feature turns the tasks developers repeat often into persistent, rerunnable workflows. In this post we look at what the feature offers, why it matters for software teams and where agent-based development tools are heading.
Anthropic's new flagship Claude Opus 4.7 arrived with improvements in coding and visual analysis. According to the company's own system card, the new model did not reach the performance of Mythos Preview, which is offered to select enterprise partners. We looked at the launch details, pricing and the Mythos comparison.
90 articles about Coding, often together with AI, Technology, LLM. The newest one is "Anthropic Unveils Claude Fable 5.2 and Mythos 5.2: Frontier AI for Coding, Science, and Cybersecurity".