Full-text search across 56595 articles. Combine with topic and date filters; results sorted by relevance.
A developer tested two AI coding assistants on a security-sensitive prompt asking for a login endpoint and found both produced secure code, including parameterized queries, proper password hashing, and timing-attack miti…
Muse released Muse Code in beta, a terminal coding agent powered by Muse Spark 1.2, which handles complete software engineering tasks across large repositories. Muse Code uses background agents that build context over ti…
Cursor's two-year aggregated usage data reveals that 90% of its token consumption is input tokens, with a 10:1 read-to-write ratio, and that the top 1% of users generate 30,000-40,000 lines of code per week, compared to …
Anthropic's Claude Code now writes 90% of the company's own codebase, boosting engineer output by 200% and shifting bottlenecks to code review. The tool's Code Review product increased substantive pull request comments f…
A developer draws parallels between coding with Claude Code and playing video games like Civilization, Dota 2, and StarCraft, noting that the loop of prompting and responding in LLM conversations mirrors game mechanics. …
LearnThat, a new remote HTTP MCP server, enables coding agents to integrate small learning exercises into development workflows by adding coaching tools such as level assessments, micro-challenges, and short-answer gradi…
A developer has published a method to run Claude Code for free by pointing the agentic coding tool at local models or free cloud endpoints instead of paid subscriptions. The approach uses shell scripts to configure Claud…
Stably AI released Orca v1.4.215, an MIT-licensed workspace that runs multiple CLI AI coding agents — including Claude Code, Codex, Cursor, OpenCode, GitHub Copilot and Qwen Code — side by side, each in its own Git workt…
Apache released Casbin Gateway, a local security gateway that installs with a single command and runs on http://localhost:17000 to govern the AI coding agents on a machine. The tool compiles roughly forty switches over e…
A developer reports that AI-assisted coding has shifted their bottleneck from implementation to review, validation, and integration, noting that faster code generation does not necessarily speed up delivery. The develope…
Zed editor's AI features enable a 'vibe coding' workflow where developers steer LLMs through projects by describing intent, with Claude 3.5 Sonnet recommended for coding logic. The guide details setting up Zed with API k…
Cycode announced Agentic Code Scanning, a fourth scanning dimension that runs deterministic and agentic code analysis as one system, alongside new Attack Chaining that links related findings into multi-step exploit paths…
Developer and open-source maintainer Mario Zechner's minimal coding agent Pi has become the author's preferred AI coding harness, offering a command-line environment with only four core tools—read, write, edit, and bash—…
AI coding agents may eliminate the inevitability of 'big balls of mud'—sprawling, hard-to-maintain codebases—by enabling developers to implement features quickly while adhering to design standards, according to an InfoWo…
JetBrains' AI Coding Agent Adoption Trends report, based on surveys of 15,000+ professional developers from May through July 2026, shows GitHub Copilot's adoption fell from 29% to 21% in 12 months, OpenAI Codex surged fr…
Pieter Levels' public ledger of roughly 113 projects, with about 9 marked a success, reveals that most of his vibe-coding ventures never earned money, contrasting with his fly.pieter.com AI flight game reaching $1M in an…
Meta's Muse Glimmer 30B model can be run locally on an RTX 3090 GPU using llama.cpp, DFlash speculative decoding, and Pi, achieving speeds of 46 to 127 tokens per second for agentic coding tasks. The guide from the local…
A developer's session logs show Claude Code processed 8.98 billion input tokens and 21.8 million output tokens across 15 desktop and 16 laptop active days, while Codex processed 5.82 billion input and 19.9 million output…
A Keras model file is executable code, not data, because its config can carry marshalled CPython bytecode via Lambda layers, and Keras's safe_mode has been bypassed repeatedly, with CVEs including CVE-2025-1550 (fixed in…
Anthropic's Claude Code pricing in August 2026 shows the same tokens and model costing up to 40x more depending on whether users buy seats or pay per token, according to a report by Pragmatic Engineer. For example, a $10…