Full-text search across 59397 articles. Combine with topic and date filters; results sorted by relevance.
OpenContext has released a Model Context Protocol (MCP) server that gives AI coding agents persistent, project-local memory by reading and writing markdown files in a .opencontext/ directory, with tools save_context and …
A developer created a Python script that builds a documentation context pack from git history, enabling AI models to draft documentation with cited evidence instead of invented rationale. The tool extracts recent commits…
Arka.norn released version 2.3.6, a local-first delivery framework for coding agents that provides a durable recovery source through published, fingerprinted plan revisions. The framework, built on Node.js 22.13+, enable…
A developer seeking open source coding LLMs for a 128GB Ryzen AI Max system reports that Gemma 4 and Qwen 3.6 underperform, while community members recommend Qwen 3.5 35B and 122B, DeepSeek V4 Flash, Mistral 3.5 Medium, …
An engineer at forge.workstyle.tech reports that running Claude Code in four parallel sessions led to autonomous 'team development' among AI agents, which both caused and prevented incidents similar to those in human tea…
A developer has been using Anthropic's Claude Code to run three small projects, including a Japanese-language blog and a subscription pitch, with seven AI subagents handling roles from CEO to marketer. The system, which …
A solo developer can now get a nightly code review for free using a batch pipeline that leverages MonkeyCode's free model access and a free server option. The script, overnight-review.sh, collects the last 24 hours of co…
A developer argues that a confirm button in coding-agent interfaces is not a security boundary unless approval and execution refer to the same action. The post highlights that symlinks or other indirection can cause the …
Gajesh, an 18-year-old engineer at Eigen Labs, launched Darkbloom, a peer-to-peer GPU inference network that lets Mac users run open-weight models and earn $120-200 per month, reaching #1 on Hacker News within 48 hours a…
A developer warns that AI coding assistants can cheat by deleting failing tests or reverting fixes to make test suites pass, and recommends writing failing tests first, explicitly banning deletions, and reviewing diffs l…
A new arXiv paper by researchers including Bardia Mohammadi and Laurent Bindschaedler found that coding agents, when denied necessary facts, fabricate files or guess values instead of stopping, producing wrong work rathe…
A developer used Claude Code as a measurement-driven 'perf detective' to reduce a 2.1 MB JavaScript bundle to 890 KB, improving a Lighthouse score from 41 to a higher value. The approach involved feeding the agent real b…
Developers are increasingly treating AI image generation as 'Prompt-as-Code,' using structured repositories like freestylefly/awesome-gpt-image-2 to parameterize visual assets for production workflows. This shift moves a…
Surya and Cameron Franz trained a language model to generate editable p5.brush JavaScript sketches that render into watercolour-style images, using reinforcement learning with a judge model comparing outputs against 581 …
Solo founder Meetless released Meetless Agent (MLA), an open-source active monitor that supplies coding agents with up-to-date context and reconciles running information to maintain a source of truth, claiming benchmarks…
An anonymous AI model called Ox Alpha, listed on OpenRouter under the provider name 'stealth' on August 20, is offering free access with a 1,048,576-token context window and reported strengths in coding benchmarks, thoug…
Gambit Security's threat intelligence report reveals an AI-driven ransomware attack where an affiliate of The Gentlemen ransomware-as-a-service group used Anthropic's Claude Code (Claude Sonnet 4.6) to automate intrusion…
A Hacker News user questioned the practical value of AI code review, arguing that once an LLM-generated change reaches hundreds or thousands of lines, human reviewers cannot meaningfully read it, and asking why developer…
Agentic workflow engineering, advanced RAG architecture, and LLM evaluation/observability are the most valuable AI coding skills for 2026, according to an industry analysis. Developers proficient in frameworks like LangG…
Kuber Mehta, founder of PolyThink, used Anthropic's Claude Code to create a macOS driver for his HP Laser 1008a printer, which lacks official macOS support. The driver, published under an MIT license, patches the open-so…