Full-text search across 33762 articles. Combine with topic and date filters; results sorted by relevance.
ShadowCat is a fully offline, single-file HTML page that enables data transfer between two devices by encoding files into a sequence of QR codes, designed for old phones with working cameras and browsers but non-function…
According to a study by CloudBees, the use of AI-generated code is leading to an increase in production failures and higher spending. The research highlights a significant "verification gap," indicating that organization…
ClawBattle, a new open-source benchmark that tests multimodal LLMs on code golfing tasks, which require both visual and textual understanding. It claims the benchmark avoids data contamination by using confidential, top-…
At the 2025 Google I/O conference, Google announced the stable release of Android CLI (version 1.0), a command-line tool designed to allow AI agents like Claude Code and OpenAI’s Codex to accelerate Android app developme…
OpenAI has open-sourced Symphony, an agent orchestrator that uses project-management tools like issue trackers to coordinate multiple autonomous coding agents. The system assigns tasks to dedicated agents that work indep…
As of August 2026, roughly 80% of the work handed off by Eigenwise's developer runs on a GPT model, all from inside Claude Code, thanks to a new MIT-licensed plugin called model-gateway that routes requests to ChatGPT, G…
Anthropic made three changes to Claude Code usage limits between May and July 2026, but only one is permanent: on May 6, 5-hour rate limits doubled for Pro, Max, Team, and seat-based Enterprise plans, and peak-hour throt…
MindFlock, a new open-source desktop app, lets developers run multiple AI coding agents in parallel, each isolated in its own Git worktree and tmux session, with a guided commit-to-merge workflow and optional ticket inge…
Microsoft Research published a field study showing engineers who adopted Claude Code merged 24% more pull requests, but Microsoft's Experiences and Devices division was instructed to remove the tool by June 30, 2026, for…
Freerange, a static analysis tool built on the official TypeScript API, lets developers find potential NaN, Infinity, division by zero, and out-of-bounds array indexes in TypeScript code at compile time without annotatio…
An engineer at a company built an internal benchmark to evaluate coding LLMs for production use, testing ten models on real-world tasks like Python services and JavaScript debugging. The results showed that cheaper model…
IBM announced updates to its Bob agentic software development platform, including multi-agent capabilities, parallel tool calling, and specialized workflows for Java modernization, IBM i OS, and IBM Z mainframe. The plat…
Brick, a Mixture-of-Models routing gateway, reads each prompt's capability and complexity to route queries to the best backend LLM, matching top model quality at lower cost. It offers a drop-in OpenAI-compatible endpoint…
Google has introduced GKE Agent Sandbox, a managed node pool configuration that applies gVisor-based kernel-level isolation to secure untrusted, AI-generated code in multi-tenant agentic systems. The solution intercepts …
A developer has identified the structural limits of "vibe coding"—a conversational, test-free approach to building software with AI agents. The technique works well for throwaway scripts, solo projects, and small additio…
AI coding agents have become so capable that a non-technical founder can ship a working product in a weekend, prompting venture capitalists to shift their focus from whether a startup has a technical cofounder to whether…
Uncle Bob (Robert C. Martin) advocates for not reading AI-generated code, instead relying on extensive testing to validate it. A developer explores the testing landscape this approach opens up, drawing parallels to valid…
NVIDIA's Nemotron 3 Ultra large language model, when paired with the ACE-RTL agent, achieves a 100% pass rate on the Comprehensive Verilog Design Problems (CVDP) benchmark for agentic RTL coding tasks, surpassing competi…
DeepSeek V3 generally outperforms Claude 3.5 Sonnet on raw coding benchmarks like HumanEval and MBPP, especially in C++, Rust, and mathematical implementations, while Claude 3.5 Sonnet is considered superior for high-lev…
A developer proposes GitHub Synapse, a 'Cognitive Version Control System' that tracks engineering intent and decision-making rather than just code changes. The system would create an 'Intent Graph' from pull requests, is…