Full-text search across 63995 articles. Combine with topic and date filters; results sorted by relevance.
A developer argues that as AI coding agents make implementation cheaper, verification becomes the bottleneck, because agents and their tests can share the same incomplete assumptions about what "correct" behavior means. …
Developer-built iOS app Sojourn: Topical Bible Study was published without the author typing a single line of code, built instead from 45 one-shot prompts using Anthropic's Claude Code and Claude Design. The Swift app us…
Agentic data analysis tools from Anthropic (Claude Code), OpenAI (GPT Codex), and open-source alternatives (OpenCode) are stochastic, producing different code on each run, which hurts reproducibility and increases costs.…
Maneshwar, a developer building LiveReview, an AI code review tool, shares seven techniques for making APIs faster, emphasizing that optimization should follow measurement and profiling. The techniques include short-TTL …
Google DeepMind released AlphaGenome Atlas, a database predicting the effects of all 9 billion possible single nucleotide variants in the human genome, using the AlphaGenome AI model to pre-calculate regulatory impact in…
Anumati, a deterministic auto-approver for AI coding agents, now supports both Claude Code and OpenAI Codex, automatically allowing safe shell commands like git status, npx tsc, and cargo test while prompting for risky o…
Agentdesktop has launched an open-source platform that inventories AI developer tools, MCP servers, and skills across employee workstations, applies tool-native configuration and sandbox policy, and routes tools through …
A developer with 15 years of coding experience built GitWarren, a free, open-source, fully local code review app that provides a GitHub-like PR experience before commits are pushed. The tool works directly with the worki…
A developer building Sirro, a hosted memory layer for AI coding agents served over MCP, shares lessons from production deployment. The project aims to preserve valuable work from coding-agent conversations, and the devel…
A developer known as mukes555 has built Tracon, a local flight recorder for AI coding agents that tracks their commands, file edits, and installs on Mac and Windows. The tool, largely written by Claude Code, flagged its …
Meta Platforms released Muse Spark 1.3 on September 2, cutting tool calls by 20% and token usage by 25% compared to Muse Spark 1.2, according to CEO Mark Zuckerberg. The update, available through Muse Code and the Meta M…
Anthropic removed over 80% of Claude Code's system prompt for Claude Opus 5 and Claude Fable 5 with no loss in coding evaluations, demonstrating that system prompts have a shelf life as models improve. The developer argu…
Supafork, a new platform at beta.supafork.com, offers a GitHub-style home for AI agent sessions, enabling users to save, fork, and share sessions across coding harnesses like Claude Code and Codex. The tool features cros…
Meta is releasing Muse Voice Transcribe, a real-time speech model that combines streaming transcription, speaker diarization, and endpointing, capable of handling 20 or more speakers and code-switching, with API access p…
Varshith Reddy, an independent student and open-source developer, has requested a Hugging Face Community Hardware Grant to host ARIA (AI-Powered Repository Intelligence Agent), an MIT-licensed developer platform for anal…
Greptile, an AI code-review startup that reviews 5B lines of code monthly for 22,000+ customers and has raised $30M from Benchmark, Y Combinator, Paul Graham, and Initialized, is hiring a Security Engineer in San Francis…
Software engineers should stop using LLMs to write implementation logic and instead use them as requirements architects, according to a new essay. The approach involves eliciting requirements, generating formal specifica…
A team of three interns built Superconnected, an email follow-up and relationship-management application, over a summer internship using AI-assisted development tools alongside Ninchi, a code-comprehension verification t…
Mads Lorentzen, a laid-off geophysicist, built ai-job-search, a Claude Code framework that hit 33,000 stars and nearly 12,000 forks on GitHub after reaching #1 trending in July. The repo, which helped him land a job as a…
Book-to-skill, a GitHub project with 24k stars and 2.6k forks, converts PDFs and EPUBs into Claude Code skills, distilling technical books into a SKILL.md file and per-chapter files that agents load on demand. The tool, …