Full-text search across 63183 articles. Combine with topic and date filters; results sorted by relevance.
This article explains how to build a supervisor-based multi-agent architecture in pure Python without using external frameworks. It describes the "Supervisor Pattern," where a central orchestrator coordinates specialized…
Based on the provided text, the article contains the source code for a batch file titled "BLUE MOON V6.5". The program presents a text-based menu with options to launch web applications, generate random usernames and pas…
The article describes the problem of "architectural drift" in AI-assisted coding, where AI agents forget past project decisions (like database choices or rejected libraries) with each new session, forcing developers to r…
XAI quietly released Grok Build 0.1, a new coding model optimized for autonomous software engineering workflows, during a week when the company also disclosed $6.4 billion in infrastructure spending. The model features a…
AI Native DevCon 2026, a conference for engineering leaders taking place in London on June 1-2, which focuses on the practical challenges of deploying AI coding agents in production. Organizer Guy Podjarny notes that whi…
Zoox has built a proprietary AI platform to accelerate developer productivity using large language models, addressing the slow information discovery and onboarding process that can take new engineers weeks before they wr…
Claude Desktop's three tabs — Chat, Cowork, and Code — operate as separate applications with distinct execution layers, memory systems, and sandboxes, not as views of the same product. Instructions, files, and preference…
Researchers introduced FrontierCS 2, a benchmark of 48 open-ended tasks that tests whether LLM agents can contribute to frontier computer science R&D by taking a paper and its released code, deleting the paper's contribu…
Running AI agents autonomously on open-source code inside isolated sandboxes lets teams get value from agents without granting them access to sensitive data or production infrastructure, according to a government practit…
Google's Gemini 4 Argon generated working Rust code for a blog-post filename function on the first attempt, producing the output in 15.2 seconds using 1,178 tokens at a cost of $0.014, according to a first-hand account. …
DietrichGebert's ponytail middleware skill layer trains LLM coding agents to use native web primitives instead of large dependency trees, cutting code generation volume by 54% while maintaining strict safety invariants, …
Otōto 2.7 fixes a macOS code-signing bug in beta 2.6 that caused macOS to terminate the app when plugins loaded, which broke Claude Code's registration so that `claude mcp get ototo` reported failure. The release adds an…
A financially motivated threat actor used a large language model to craft PhantomRaven, a JavaScript information stealer whose code shows telltale signs of AI involvement including verbose comments and placeholder code, …
A developer reports that using AI agents for coding on large, legacy-heavy repositories increases cognitive load, requiring hyper-detailed specs, line-by-line code reviews, and manual dependency tracing that often exceed…
Netherite, a new AI security tool, scans entire code repositories to identify exploitable vulnerabilities, providing detailed findings with file, line, and reasoning, along with a fix prompt that can be pasted into a cod…
MonkeyCode, an open-source AI coding project offering free model access and a free server option, was field-tested to measure how far its 10-million-token allowance goes on realistic coding tasks. The test harness, built…
A Hacker News user asked whether AI's training on existing code will trigger mass intellectual property protectionism in software, as developers may become reluctant to share original code without attribution or financia…
Cognition AI's Devin, an AI coding agent, now supports the Agent Client Protocol (ACP), enabling direct client-to-agent communication beyond its default terminal UI, as detailed in a QAInsights post. The protocol standar…
The maintainers of an unnamed AI agent project deprecated generic agent skills such as multi-step workflow templates, web wrapper skills, and prompt chains for code review because newer versions of Claude Code, an AI cod…
Poolside AI's Laguna XS model, a small local LLM, performed well in refactoring Rust code via OpenCode, making relatively few errors and handling tool calls correctly except for escaped quotes. The 20.3 GB 4-bit quantize…