Full-text search across 61901 articles. Combine with topic and date filters; results sorted by relevance.
Matt Shumer, founder of AI startup AnswerAI, published a technique called the Gauntlet Loop after using it to build a Call of Duty-style game from a single prompt with Claude Opus 5 in Claude Code. The method involves a …
A developer who calls themselves a '0.1x developer' argues against the modern interpretation of the '10x developer' as someone who prioritizes code production speed, especially with the rise of LLMs and vibe coding. The …
QualityMax launched 9lives, a self-healing test runner that automatically fixes broken Playwright, Cypress, and Selenium tests by repairing drifted selectors without masking real bugs. The tool uses offline selector repa…
Strix, an open-source AI penetration testing agent, reached 34,000 GitHub stars this week as a response to a surge in security vulnerabilities from AI-generated code. CVEs traced to AI-written code jumped from 6 in Janua…
A developer argues that comparing a senior engineer's $250K salary to $20K in AI coding tokens is a misleading trap. The engineer's role involves far more than code generation, and AI-written code still requires senior h…
BuildForever has integrated an AI teammate named Avery into its engineering workflow, which autonomously wrote 31% of the code shipped by its five-engineer team last week. Avery identifies issues, diagnoses root causes, …
A developer documented a secret scanning setup that prevents credentials from entering the context window of Claude Code, an AI coding assistant. The system uses trufflehog with 700+ detectors to intercept secrets at fou…
John D. Cook used Anthropic's Claude (Sonnet 4.6 Medium) to find a typo in a blog post about quaternion rotations by asking it to write Lean code verifying the post's theorems. After four iterations, Claude produced corr…
Repowire, a new open-source tool, connects multiple coding agents like Claude Code and Codex across different repositories, allowing them to pass messages and coordinate tasks without manual copy-paste. The system runs l…
Polarized state of software development in 2026, divided between "token chasers" who use AI to rapidly ship code and "refusers" who write every line by hand. It argues that both sides have valid points: AI can dramatical…
Researchers at Microsoft have introduced AutoSP, a compiler-based solution that automatically converts standard training code into multi-GPU sequence parallel code for long-context language model training. The tool, inte…
Recursive released Recursive Flint, a mixture-of-experts coding model with 40 billion total parameters that activates 2.5 billion per token, which the company says leads MoE models under 50 billion total parameters on ag…
AlbertCode released version 1.54 of its SWE Agent, a free-to-install AI coding agent for macOS, Windows and Linux that plans changes, builds them in an isolated copy of the repository, runs the project's own tests, and a…
A 720-trial experiment by Bonsai found that telling Claude Haiku 5.5 and Claude Sonnet 5.5 not to base new code on an existing file dropped the models' usual answer — a sliding window log, chosen 88% of the time with no …
Stack Overflow's 2026 Developer Survey, covering 30,000 developers across 169 countries, found that 65% use AI coding agents daily while 58% of those users actively try to avoid them, and 46% do not trust AI tool output …
Reporails released Claude Mods, a set of classic desktop games packaged as Claude Code plugins, starting with a Minesweeper game called minefield that runs in a side pane while Claude works. The mods require Claude Code …
Measuremy.site launched Agentlytics, a cookieless website analytics product that exposes 12 tools over the Model Context Protocol so coding agents such as Claude Code, Cursor and Codex can read traffic data and act on it…
Knack appointed Tim Costantino, formerly Senior Vice President and Head of Product at AdvancedMD, as Chief Product Officer to lead product strategy and its healthcare offering, Knack Health. The no-code platform launched…
A study from ETH Zurich and LogicStar (arXiv:2602.11988) found that developer-written AGENTS.md context files improved coding agent success by about 2.4 points in its revised June 2026 version, while LLM-generated files …
A personal LLM user reports that Qwen3.8-27B running locally via llama.cpp on an RTX 5090 laptop GPU with 24 GB of VRAM now handles Q&A, coding, sysadmin and web research without a cloud provider, delivering roughly 60–3…