Full-text search across 58891 articles. Combine with topic and date filters; results sorted by relevance.
A developer built a circuit breaker for Claude Code's weekly quota after 15 LaunchAgent jobs silently failed for six hours, costing ¥1.2M/month in lost automation. The tool, claude-quota-guard.py, detects quota-limit err…
Oracle Health, the healthcare arm of Oracle Corporation, expanded its Clinical AI Agent on August 19, 2026, adding automated professional fee coding, real-time dictation, and AI-assisted chart review for U.S. health syst…
Vercel Labs open-sourced fx, a coding agent CLI written in Zig that ships as a 7.8 MiB binary, cold-starts in 10 microseconds, and requires no runtime to install. The tool, currently at v0.0.4, is designed for embedding …
A developer proposes a 'dark factory' pipeline for AI-assisted coding, where an automated system uses separate models for building and adversarial verification, with sampled human audits. The approach aims to cut review …
Cisco's Foundation AI team released Antares-1B, a 1 billion parameter open-weight model that localizes software vulnerabilities in code repositories and runs on a single GPU, consuming under 5GB of VRAM in testing. Built…
Coding agent companies should build trust by making real usage and failure modes visible in their communities, rather than relying on polished demos, according to a blog post on Hacker News. The post argues that develope…
Chinese AI developer Zhipu has launched GLM-5.3, a coding-focused AI model that scored 84.5% on CyberGym, ahead of Anthropic's Mythos 5 (83.8%) and OpenAI's GPT-5.6 Sol (83.6%), but trails both on ExploitBench with 54.4%…
Microsoft's monthly Windows security fixes surged from 60-90 last year to a record 600+ in July 2026, with Oracle and Linux following suit, driven by AI's dual role in both accelerating bug discovery and generating flawe…
Z.ai unveiled GLM-5.3 on August 14, reporting improved performance on long-horizon coding and software-vulnerability analysis. The model scored 84.5% on Z.ai's CyberGym benchmark, above the company's reported 83.8% for A…
A developer has built a dual-backend setup for Claude Code, routing cheaper tasks through a self-hosted LiteLLM proxy to DeepSeek models while keeping a full Anthropic subscription for trusted work. The key trick is poin…
Windsurf has been rebranded as Devin Desktop following Cognition's acquisition, and Cursor became a SpaceX subsidiary on August 14, making the editor comparison obsolete. Claude Code, with annualized revenue of $2.5 bill…
Google's Gemini 3.7 Flash model cuts inference costs by half while improving code generation accuracy, with FrontierCode scores rising from 34.4% to 43.6%. Z.ai's GLM 5.2, a 1M-token open-weights model, is now the defaul…
A new guide from an unnamed source outlines five routes to free AI coding in 2026, finding that only local open-weight models avoid ongoing token costs, while the most-cited $5 trial credit covers as few as zero tasks on…
A developer used Anthropic's Claude Code to debug a checkout API whose p99 latency had crept to 2.1 seconds. The AI assistant analyzed trace data, identified that orders with more than 12 line items were disproportionate…
Anthropic will make Auto Mode, an automated classifier that screens tool calls in real time, the default permission setting for Claude Code Pro, Max, and Team subscribers starting August 14, 2026, replacing manual approv…
Dan Luu's large-scale evaluations show that the token-efficiency advantage of terse programming languages for AI coding agents largely disappears on real tasks, contradicting a widely cited claim. In tests where agents i…
Yeeth Security researchers identified a malicious Visual Studio Code extension named 'Solidity Pro' that targets cryptocurrency developers with a multi-stage attack, ultimately running independent Python malware on victi…
A developer outlines seven practical Claude Code projects that address real business problems, such as a prospect research tool for sales teams, an internal knowledge assistant, and an automated client reporting workflow…
A backend engineer on Hacker News reported that after using AI to code for half a year, he forgot how to handwrite a JSON parser, a skill he once had mastered. The engineer's experience, which drew hundreds of replies fr…
BoundaryBench, a new open-source benchmark from the developer community, measures how much capability coding agents lose when running inside enterprise/NIST-derived hardened sandboxes, with live results showing Grok Buil…