Full-text search across 62852 articles. Combine with topic and date filters; results sorted by relevance.
Software engineering is fundamentally about managing complexity and making architectural tradeoffs, not just writing code, according to a new essay. The piece argues that while AI excels at generating code, it cannot rep…
Xenition, an AI-native app builder, aims to let developers create mobile apps by describing their intent in natural language rather than writing code. The project's approach focuses on generating visual previews and shor…
SemiAnalysis announced AgentX 1.0, the world's first fully open source multi-turn agentic coding inference benchmark at 1 million context, released under Apache 2.0, after spending more than $3M building the dataset. The…
XAI's Grok Build coding CLI, released with the Grok 4.5 model, was found to upload users' entire repositories, including .env secrets and git history, to xAI's cloud storage without consent, according to independent AI s…
Z.ai launched GLM-5.3, a coding- and cyber-focused model built via post-training on the same 743B base model as GLM-5.2, achieving scores of 28.3 on Terminal Bench 3.0, 66.9 on DeepSWE, 28.5 on Agents' Last Exam, and 176…
Databricks launched Smart Routing in Unity AI Gateway, now in Beta, which automatically matches coding tasks to the most cost-effective model and harness, achieving 30%+ lower cost per task while matching frontier qualit…
A configuration using the DFlash speculative decoding drafter with Meta Muse Glimmer 30B on an NVIDIA RTX PRO 4000 Blackwell SFF GPU reached 84.64 tokens per second on a coding task, a 4.50 times speedup over regular dec…
Matt Asay, writing in 2014, argued that enterprises should open source internal software to involve users in improvements, turning organizational problems into industry consensus. Twelve years later, with AI making code …
A developer found that Ponytail, a tool making AI agents write minimal code, caused a dangerous race condition that double-charged a customer. Switching to Guardsman, which challenges changes for safety and convention co…
Geoffrey Litt argued at the AI Engineer conference in July 2026 that understanding code written by AI agents remains crucial for effective collaboration, proposing techniques like code explainer docs, quizzes, and intera…
A developer distinguishes three layers of the AI agent stack through open-source projects: Pi as an agent kernel and toolkit, Goose as a local agent workbench, and OpenCode as a coding-first software-development agent. P…
A dispute between Papermark and Y Combinator-backed Corgi highlights how AI-assisted development complicates open-source copyright claims, as Papermark alleges Corgi used AI to replicate its product's protected expressio…
Enterprise AI coding adoption has shifted from experimentation to infrastructure, with cost control and usage visibility becoming top priorities. At Gartner's summit, attendees focused on managing spiraling AI costs, as …
A controlled study by a model evaluation organization found that open source developers using AI coding tools were 20% less productive despite believing they were 20% faster. The gains from AI-assisted coding are absorbe…
A developer released two open-source templates for Claude Code and OpenAI Codex that prevent AI coding agents from forgetting project context by storing rules and decisions in files and automatically injecting them via h…
A developer implements a system where Claude Code writes code diffs and a separate Codex model reviews them before human approval, using cross-model disagreement to catch bugs that self-review misses. The hook-based work…
Cursor and SpaceX have agreed to co-develop coding and knowledge agent models, with SpaceX holding an option to acquire Cursor for $60 billion or pay $10 billion instead. The deal aims to combine Cursor's coding product …
Cloudflare is releasing the Cloudflare Agents SDK, a platform layer providing durable execution, dynamic code execution, and other primitives for building production-grade AI agents, and is launching Flue, an open-source…
Anthropic released Claude Opus 4.8 on Tuesday, pricing the new model at $5 per million input tokens and $25 per million output tokens — the same as its predecessor. The company claims the model is its strongest coding mo…
A critical remote code execution vulnerability, tracked as CVE-2026-40933, has been discovered in Flowise, an open-source platform for building LLM workflows and AI agents. The flaw exists in Flowise's Custom MCP tool su…