Full-text search across 64105 articles. Combine with topic and date filters; results sorted by relevance.
Caveman 2, an MIT-licensed add-on for coding agents including Claude Code, Codex, Gemini, Cursor, and Windsurf, shipped version 1.10 this week, cutting input tokens by 33.2% via a new local proxy and output tokens by 65%…
Figma is becoming a graveyard for small AI-driven teams, according to a developer's account, as reliance on AI-generated frontend code leads to a spike in minor UI bugs and visual inconsistencies. The developer notes tha…
Cursor announced on August 13, 2026, that it is acqui-hiring the Firetiger team, founded in 2024 by Rustam Lalkaka and Achille Roussel, to integrate production monitoring into its coding platform and build agents that ca…
Omarchy's upcoming release, Quattro (4.0), will integrate AI agents into the Linux desktop, a move its creator David Heinemeier Hansson says will 'truly democratize Linux' and boost developer adoption. The beta includes …
A developer examines the emerging role of the 'AI Product Builder,' a hybrid of product manager and developer enabled by advances in code harnesses. The role's success depends on the maturity of the codebase and environm…
A developer's essay argues that using LLM coding agents like OpenAI's Codex turns every new project into a brownfield project, requiring developers to understand and work with unfamiliar generated code, which undermines …
SpaceXAI and Cursor launched Grok 4.5 on July 16, a frontier model for coding and agentic tasks, available across Cursor's desktop, web, iOS, CLI, and SDK at $2 per million input tokens and $6 per million output tokens. …
David Heinemeier Hansson, creator of Ruby on Rails and co-owner and CTO of 37signals, said in an August 11th post on X that working with AI has restored a creative urgency he had not felt since his early days with Ruby, …
Anthropic has signed the EU Code of Practice on Transparency of AI-generated Content, committing to mark AI-generated text as part of Europe's transparency regime, which took effect with Article 50 of the EU AI Act on Au…
Jeff Wang, President of New Enterprise at Cognition, said AI coding agents now handle roughly 40% of the workload at Cognition, and Devin automatically fixes 70% of vulnerabilities at some large banks. The company merged…
An open source maintainer is calling out 'drive-by' pull requests, where contributors submit code with no intention of iterating, often generated by AI and submitted en masse for GitHub contribution squares. The develope…
Docker launched Sandboxes, disposable microVM environments for AI coding agents, which reached the top of Hacker News with 285 points. The product uses libkrun-based microVMs with isolated kernels and network stacks, and…
A developer built a shared markdown 'blackboard' to coordinate multiple parallel Claude Code sessions after discovering that parallel AI agents collide because they lack shared context. The developer found that the indus…
A developer has published a guide for configuring Anthropic's Claude Code CLI to route requests through OpenRouter, enabling the use of DeepSeek's v4 Flash model instead of Anthropic's default models. The setup involves …
A team at an unnamed company found that adding more context to coding agents, such as spec files and instruction rules, degrades their performance past a certain point, leading to confusion and incorrect outputs. The tea…
Make This Better launched a feedback widget that captures annotated screenshots, console errors, and DOM state, and uses AI triage to turn user reports into tasks for coding agents like Claude Code, Cursor, and Codex. Th…
OpenAI announced on June 11 that it will acquire Ona, the German cloud startup formerly known as Gitpod, to integrate its cloud workspace technology into the Codex coding agent. Codex now has more than 5 million weekly u…
AI agents now perform real work, but companies lack automated checks for judgment-based tasks like writing and strategy, according to an essay by an unnamed author on Inside AI Native. The author argues that while determ…
Software engineer and blogger Simon Willison warns against relaying AI-generated responses verbatim in communication, calling it 'meat proxy' behavior that adds no value. He advises reading, understanding, and validating…
DeepSeek's V4-Flash model exited preview and is now available in public beta, with benchmark scores surpassing V4-Pro-Preview and native agent support, according to a tweet from DeepSeek. The author describes a setup usi…