Full-text search across 56595 articles. Combine with topic and date filters; results sorted by relevance.
Alphabet CEO Sundar Pichai said on the July 22 Q2 earnings call that coding and agentic coding are areas Google needs to improve, as Google disclosed that its Gemini 4 model has entered its most ambitious pretraining run…
A developer argues that AI coding harnesses like Claude Code, Codex, Antigravity, and OpenCode can be used for deterministic data engineering by having agents author artifacts at development time rather than at runtime. …
A developer building AI and CI tools that run untrusted code outlines a security field guide for safely executing code from pull requests. The guide emphasizes that the real risk is not malicious code in diffs but the au…
Researchers demonstrated indirect prompt injection attacks against Anthropic's Claude Code, achieving remote code execution in 10 out of 10 experiments using a model downgrade attack and inspection fatigue. The attack ex…
AxDafny, a verifier-guided framework, achieved a 92.7% verification success rate on DafnyBench, outperforming GPT-5.5 by 6.5 percentage points. The tool generates code with proof artifacts, setting a new benchmark in aut…
AI now writes nearly all code at startups like Alma, Chainguard, and Wordsmith AI, with Anthropic's Claude Code as the dominant tool. Founders report massive speed gains but also warn of a 'cleanup tax' from bugs and slo…
Baz improved its AI Agent Code Review accuracy by building a Spec Review agent using Amazon Bedrock AgentCore, automating the validation of code against product and design requirements. The system orchestrates multi-stag…
A developer built a nine-agent AI development team as a Claude Code plugin, orchestrating specialized agents to take a feature request from requirements analysis through production deployment. The plugin, called claude-d…
Software developers returning from maternity leave are finding their jobs transformed by AI coding tools that became standard during their absence, leaving new mothers struggling to catch up with colleagues who gained mo…
A developer has combined "vibe coding" with spec-driven development (SDD) to create a hybrid workflow that balances rapid prototyping with codebase stability. The approach involves writing a lightweight, 15-30 minute spe…
Vilius Vystartas tested 10 large language models on 10 coding tasks to determine whether prompting them to write efficient code actually improves output. Only four models showed measurable gains, with GPT-5.4 achieving t…
A solution to the frustration of switching between coding agents Claude Code and Codex by integrating both into a single chat window. The author implemented a mode-switching system using simple commands like `/cligate` f…
A developer built RepoPilot, a deterministic, LLM-free tool that flags when coding agents weaken test checks, after labeling 358 public pull requests that modified test code. In a small experiment, Codex never weakened t…
A developer built Claude Code Token Optimizer, a free, MIT-licensed VS Code extension that parses the JSONL session transcripts Claude Code writes to ~/.claude/projects/ and displays estimated spending, token usage, and …
Developer vshvedov released Rhun v0.16.2, an open-source code editor written in assembly, available for Linux and macOS via a curl install script and for Windows as a ZIP download. Rhun offers tabs, syntax highlighting, …
Unity Technologies released official plugins for Anthropic's Claude Code and OpenAI's Codex that give the coding agents Unity-specific skills written and maintained by Unity teams, with the Codex version launching with 3…
Cline, an open source autonomous coding agent licensed under Apache 2.0, has surpassed 67,000 GitHub stars and 7,000 forks, positioning itself as a free alternative to proprietary tools like Claude Code and Cursor. Built…
Nexpath, a middleware layer that appends verification steps, constraints, and acceptance criteria to AI coding prompts, improved Claude Code's performance on SWE-bench Verified from 27 of 40 tasks solved to 29 of 40, acc…
A developer running custom simulation software has moved from cloud-based AI coding assistance to local inference on high-end HPC equipment, using Hermes, Ollama, vLLM, and SGLang with models like Qwen3.8-27B. The setup …
SlideOps, a new tool from developer glukicov, generates slide decks from a repository's code and flags when the slides drift from the code, treating documentation as a build artifact. It works as a pair of Agent Skills f…