Full-text search across 66059 articles. Combine with topic and date filters; results sorted by relevance.
Anthropic's engineering teams are increasingly relying on AI for code review and testing, with a 500K+ line Bun rewrite to Rust completed in 11 days using AI tools at a cost of $165,000 in tokens. The Claude Platform tea…
This article, the first in a series on agentic engineering, argues that neither the hype claiming AI will make software engineers obsolete nor the reassurance that AI is just another tool is honest. The author observes t…
Aikido Security's "State of AI in Pentesting 2026" report found that 76% of teams ship significant changes at least weekly and nearly 40% ship daily, yet only 21% validate security on every release, with 48% saying pente…
Moonshot AI released Kimi K3 in July 2026 as a 2.8T-parameter open-weight MoE model with a 1M token context window and native vision support, scoring 88.3 on Terminal-Bench 2.1, close to top closed models like GPT-5.6 So…
Tlamatini, a locally-deployed AI developer assistant named after the Nahuatl word for "one who knows," now features 68 drag-and-drop agents following its v1.9.0 release. The tool combines a hybrid RAG pipeline with a mul…
Cognition avoids multi-agent systems for coding tasks because they suffer from context loss, akin to a "game of telephone," where critical information is miscommunicated between agents. The company found that single agen…
JetBrains' refactoring-skill benchmark, published August 19, 2026, reports that its AI skill for Rider and ReSharper is 83% faster, 64% cheaper, and uses 63% fewer tool calls, based on median results across fifteen C# re…
Snyk's benchmark of ~150 vulnerable code samples in JavaScript, Java, and Python found that out-of-the-box frontier models cluster at 72–75% secure-and-functional fix rates, but Snyk Intelligence (the agentic Agent Fix a…
In a podcast, Michael Stiefel spoke with Sarah Wells about governance in software architecture and its application to agentic AI development. Wells argued that governance enables teams to reduce complexity and improve se…
Microsoft's TypeScript team rewrote the TypeScript 7.0 compiler and tools in Go, achieving roughly an order of magnitude improvement in build times. The decision reflects Go's design for readability and maintainability a…
Anthropic and OpenAI have acquired package manager companies Bun and Astral respectively, signaling growing interest from frontier AI labs in these software development tools. Package managers are programs that handle th…
The Swift Concurrency Manifesto, authored by Chris Lattner, outlines a long-term vision for introducing a first-class concurrency model to Swift, focusing on task-based abstractions like async/await and actors to elimina…
A practical buyer's guide for non-engineers recommends that citizen developers choose an AI app builder that ships a real backend, database, and authentication, not just a demo, and highlights Remy as a spec-driven alter…
Anthropic's Claude Code team and community advisors have shifted from recommending accretion—adding a rule to CLAUDE.md every time the model errs—to ablation, advising users to delete the file periodically and add back o…
A data engineer with 20 years of experience argues that while AI scepticism is valid, large language models (LLMs) offer powerful capabilities for software development that should be adopted with guardrails. The author c…
Researchers introduced AdaMAST, an adaptive extension of MAST, which converts an LLM agent's execution traces into a taxonomy of named failure codes along three fixed axes, enabling durable and diagnostic failure feedbac…
The article provides a detailed analysis of the unique font used in the Commodore 64 "Dead Test" diagnostic cartridge, which is embedded in the cartridge's ROM to function independently of the C64's built-in character se…
Microsoft's 14 October Patch Tuesday release carried 1,418 Microsoft-authored CVEs, 77 of them rated critical, with working exploit code confirmed for only three, according to the CVRF temporal vector cited in the brief.…
OpenAI's GPT-6 Astra requires noticeably less hand-holding than prior models like Opus, making fewer wrong assumptions about developer intent, according to hands-on testing described in a step-by-step guide to building a…
Kunal Jaura released isitsecure, an open-source command-line tool that combines SAST, DAST, and LLM-powered code review into a single security scanner for web applications. The tool supports multiple languages and framew…