Full-text search across 63916 articles. Combine with topic and date filters; results sorted by relevance.
A new analysis by an unnamed author suggests that large language models (LLMs) perform well on tasks with few requirements, such as vibe coding, security testing, and short creative works, but struggle with tasks that ha…
Alibaba's Qwen team released Qwen-MM-Plugins, a suite of native multimodal plugins that add vision, video, and 3D capabilities to Qwen models and any agent harness. The plugins install as skills plus optional MCP servers…
A developer highlights the shortcomings of using Figma screenshots as input for AI design-to-code tools, arguing that screenshots lose critical layout, semantic, and token information. The developer introduces figmascope…
A developer has created a minimal CLI agent in C that can perform tasks similar to Claude Code, using only 2MB of RAM and negligible CPU usage. The single-file program, named cgent, relies solely on libcurl and the OpenA…
Measurement fraud in AI-assisted development occurs when the same AI agent that writes code also writes and grades its own tests, causing evaluations to pass while code is broken, according to a report by Asif Waliuddin.…
Alberto Arena, a Laravel developer, reports that his deterministic code generator for event sourcing in Laravel, albertoarena/laravel-event-sourcing-generator, has surpassed 10,000 downloads on Packagist, while his newer…
The Rust project's compiler, libs, types, rustdoc, and bootstrap teams adopted a formal policy on August 5, 2026, governing large language model use in the rust-lang/rust repository, as announced by policy author Jynn Ne…
Aikido Security launched Aikido Machine, an on-premises GPU server that runs its AI pentesting and AI Code Analysis entirely within a customer's network, ensuring no source code, repositories, or prompts leave the infras…
Data gravity is compounding integration debt in API-first AI stacks, making vendor lock-in a gradual process that most teams drift into rather than choose, according to a technical analysis by Glukhov. The article identi…
Context Goblin, a code review tool, claims that while all major competitors now read entire repositories, it uniquely reasons across repository boundaries and integrates ticket tracker context. The post cites a Martian b…
Meticulous, a startup that records real user sessions to automatically build UI test suites, has launched a solution that generates tests in under 5 minutes per pull request, addressing the flakiness problem exacerbated …
Hedgehog, a new AI engineering workflow from developer skyf0xx, enforces test-driven development and opinionated architecture to keep AI-generated codebases structured as they grow. The tool, installed via `npx @skyf0xx/…
A partially deployed four-layer architecture for self-hosted enterprise AI, built on a local Kubernetes cluster with two isolated tenants, demonstrates that architectural trust—reliable execution guarantees independent o…
A developer on dev.to questions how to judge content quality when AI is involved, noting that many projects are AI-assisted or vibe-coded to impress recruiters, but candidates often fail to explain their work in intervie…
A11Y.md, created by Felipe Arriada Carrio, is a persistent context system and accessibility validation protocol that integrates with AI coding agents such as Cursor, Claude, and Copilot to enforce WCAG 2.2 AA and ADA com…
An unreleased OpenAI model, reportedly code-named Astra, produced solutions to open math problems, including a new lower bound for high-dimensional sphere packing that improved on a result that had stood for about 48 yea…
Developer Obaid Regens released Pivotal, an open-source universal-workspace model for agent harnesses that categorizes Claude Code activity into topics for easier resumption and context combination across chats. The tool…
A developer has developed a spec-driven development workflow for AI coding agents that uses explicit checkpoints and structured handoffs to prevent context rot and unreviewable diffs on large features. The approach treat…
A senior software engineer with 27 years of experience reports that agentic coding tools have transformed their job into a high-volume code review cycle, where reviewing generated diffs is now the primary bottleneck and …
RunInfra enables running Kimi-Linear-48B, a distilled version of the full 2.78-trillion-parameter Kimi K3 model, on a single consumer GPU such as the RTX 5090 with 32 GB VRAM, achieving 113.83 tokens per second at 3.18x …