Full-text search across 56711 articles. Combine with topic and date filters; results sorted by relevance.
Researchers introduced Terminal-Bench-LILT, a benchmark of 300 authentic coding tasks in ten languages (Arabic, Czech, German, Spanish, Hindi, Japanese, Korean, Serbian, Turkish, and Chinese) designed to evaluate coding …
Anthropic is testing whether its AI coding tool Claude Code can handle daily maintenance of the company's own software, including crash fuzzing and dead-code removal. In a few weeks, the AI created 388 pull requests, and…
Hoplite, a YC S26 startup founded by Bence and Ryan, launched a platform that deploys coding agents in the cloud, porting local setups including sessions, memories, and MCP servers. The founders built a custom agent harn…
A developer benchmarking AI coding tools found that vector-based code search and graph-based code representation each answer different questions, with neither approach universally superior. The analysis, which tested Cla…
A senior software engineer reports that they no longer hand-write much code, instead reviewing AI-generated code and designing system behavior, agents, and verification logic. The engineer argues that the bottleneck in s…
AI coding tools such as Claude Code accelerate the creation phase of software development but create a bottleneck in verification and maintenance, according to a developer's account. The efficiency gain is asymmetrical, …
A new Claude Code skill called 'crispy-comments' automatically prunes verbose code comments, removing incidental history, defensive justifications, commented-out code, and ASCII-art banners to keep only comments that hel…
A developer has released Claude Code Workflow (CCW), a generator that creates linear Spec-Driven Development workflow plugins for Claude Code from a single YAML configuration file. The tool automatically regenerates comm…
The article explains that AI coding assistants like Claude Code and Cursor face limitations when performing large-scale code refactoring because they rely on token-intensive and error-prone full-file rewrites. To overcom…
CodeRabbit is positioning independent AI code review as the trust layer for agent-generated pull requests, cloning each repository into an isolated sandbox, building a code graph, and running more than 50 linters and sec…
A developer installed the latest T3 Code nightly build and its TestFlight mobile app from pingdotgg, then ran agents across an M1 Mac mini, an M3 Max laptop, a lightweight terminal laptop, and an iPhone, using ChatGPT an…
Developer rav4nn released agent-chrome, a free open-source Claude Code plugin that lets the AI agent browse in a copy of the user's signed-in Chrome while the browser window stays behind the terminal instead of stealing …
A developer released Rexo Code v0.9, a free, open-source, provider-agnostic AI coding agent written in Rust that runs in the terminal and supports Windows, Linux, and macOS. The agent can search and edit project files, r…
AWS's Strands team released Strands Harness v0.1.0 on September 21, an open-source agent that costs $56.29 per task versus Claude Code's $248.05 on Terminal-Bench 2.1 using the same Fable 5 model, with 69.7% accuracy ver…
A comparison of AI coding agents found Cursor Pro and Windsurf both cost $20 per month while Claude Code (Beta) is pay-per-token via API, with Cursor taking about 4 seconds to index a new branch on a 140-file project. Th…
Researchers from Duke University and Tsinghua University published a paper on September 3, 2026 introducing PlaidQ, a continuous Gaussian latent-diffusion language model for code generation. Distilling the diffusion proc…
Developer affaan-m released ECC (Everything Claude Code), an open-source performance harness and operating system for AI coding agents such as Claude Code, Codex, and Cursor. ECC enforces a structured plan-test-implement…
Builder renamed its two platform products, with Fusion becoming Builder Code and Publish becoming Builder Content, the company announced in a product update. Builder Code is where customers build with AI agents on real, …
Catenary, a new spatial canvas IDE for AI coding agents, lets developers orchestrate Claude Code, Codex, Cursor, Grok, OpenCode, and Pi on an infinite canvas with visual wires, Monaco editors, and 1-click worktrees. The …
Benzi, a new code intelligence infrastructure for frontier AI models, claims to reduce source code reading by 56% compared to Claude Code Sonnet, achieving 78.2% on SWE-bench Verified for under 10 cents per fix. The tool…