Full-text search across 64092 articles. Combine with topic and date filters; results sorted by relevance.
The Cybersecurity and Infrastructure Security Agency (CISA) added CVE-2025-62593, a critical remote code execution flaw in the Ray AI framework, to its Known Exploited Vulnerabilities catalog on August 17, 2026, after co…
Corral, a free, open-source Mac app for macOS 13 and later, displays every running Claude Code, Codex, and Cursor process, showing the project each belongs to, idle time, and cost, with no permissions, telemetry, or netw…
An engineer at Veheria reports that AI agent workflows for engineering teams save about 30 minutes per engineer per day when focused on mechanical verification in code review, not on code generation. The engineer found t…
LangChain's Terminal-Bench experiment found that changing only the harness—keeping the same model—moved a coding agent from roughly 30th place into the top 5, reframing harness design as an architecture decision. Paul Iu…
A developer at Shopify used test selection to cut CI queueing from about 20 minutes to a couple of minutes for many changes, after coding agents pushed a hobby project to roughly 500,000 lines of code and made CI a bottl…
A critical sandbox escape vulnerability in isolated-vm, a JavaScript library downloaded over 1 million times per week and used in AI agent frameworks including n8n, Sim.ai, Mastra, and Activepieces, was patched in versio…
Rabih Jabr, a developer, reports that AI coding agents like Claude Code can make locally correct decisions with non-local consequences, such as force-pushing to main, because they cannot see the full impact. He proposes …
UnlimitedNIM, a streaming reverse proxy for NVIDIA's NIM free tier, eliminates 429 rate-limit errors for coding agents by enforcing a 40-request-per-minute sliding window and priority queue, with tests showing 260+ reque…
OpenCode, an open-source AI coding agent platform, offers a free multi-agent development environment through the Oh-my-opencode-slim plugin, which provides specialized agents called heroes that can be configured with dif…
Japan's government panel approved a plan to require AI firms to disclose training data under a 'principle code' for generative AI businesses, aiming to protect intellectual property rights. The code, based on a May 2025 …
A developer shares a study plan for LeetCode that emphasizes explaining the problem out loud before coding, using a rubber-duck-style script to clarify approach and edge cases. The technique, illustrated with the Two Sum…
A developer discovered that OpenAI's Codex CLI and other subscription-gated command-line tools can silently fail by printing errors to stderr while exiting with code 0 and producing empty stdout, causing automation to re…
A developer argues that AI is undermining hackathons by enabling 'happy path' demos that fail on edge cases, and urges a shift toward architectural rigor over raw code generation. The author recommends mapping state mach…
Anthropic's published system-prompt history for Claude models shows a sawtooth pattern of growth and pruning, not a monotonic ratchet, with the Opus 5 prompt at about 3,200 words after shrinking for three consecutive rel…
Anthropic's prompt caching cut API input costs by 83.9% for Traceguard's Claude Code sessions, saving $62,934 over 71 days, according to an analysis by the Traceguard team. The team found that while a low cache hit rate …
At the August Tech Talk meetup in Augusta, Jason presented a practical guide to DNS troubleshooting, emphasizing the importance of confirming that a problem is actually DNS-related before diving into fixes. He covered to…
Anthropic began embedding a statistical watermark into all Claude text output on August 2, 2026, across API, Claude.ai, Claude Code, and cloud integrations, to comply with the EU AI Act's Article 50(2) Code of Practice. …
Cursor, the AI code editor, announced that Firetiger, a startup founded in 2024 by Rustam Lalkaka and Achille Roussel, is joining Cursor. Firetiger builds agents that monitor production software, catch regressions, and i…
Jeremy Berman reported scoring 96.2% on ARC-AGI-3 with Opus 5, and 99.3% pass@2, using a program based on Claude Code and Opus 5 (high) with one action command and filesystem logs. The approach, which starts from scratch…
Caveman 2, an MIT-licensed add-on for coding agents including Claude Code, Codex, Gemini, Cursor, and Windsurf, shipped version 1.10 this week, cutting input tokens by 33.2% via a new local proxy and output tokens by 65%…