Full-text search across 63198 articles. Combine with topic and date filters; results sorted by relevance.
CrowdStrike Counter Adversary Operations researchers found that DeepSeek-R1 generates up to 50% more insecure code when prompts include politically sensitive terms such as "Falun Gong," "Uyghurs," or "Tibet," according t…
Z.ai released GLM-5.3-Flash and GLM-5.3-FlashX, the first native multimodal models in the GLM-5 series, with GLM-5.3-FlashX delivering inference speeds of 200 tokens/s. The models accept video, image, text, and file inpu…
Security researchers at Hacktron AI used Anthropic's Claude Opus 4.8 and Claude Opus 5 models to chain two vulnerabilities and take over OpenAI employees' ChatGPT and Codex accounts, reach OpenAI's internal code reposito…
AnyRouter, a third-party relay that forwards Claude Code and OpenAI Codex traffic through an Anthropic- and OpenAI-compatible endpoint at anyrouter.top, advertises a $50 free signup credit with no credit card required pl…
Browser Use and Stagehand both automate browser tasks with AI, but Browser Use suits users who want the agent to choose browser steps while Stagehand v4 suits those who control the sequence in application code, according…
GeekyAnts launched AntFlow AI, an agentic software development framework that applies spec-driven development with multi-agent execution, independent AI code review, traceability, and repository workflows. GeekyAnts clai…
Amazon Web Services added a Consent portal to AgentCore Identity, a capability of Amazon Bedrock AgentCore, giving customers a managed web experience and session binding endpoint for the AgentCore Gateway three-legged OA…
Cline released Cline Desktop, an early open-source Mac app for running open-weight models that brings the company's agent harness to a dedicated workspace with parallel sessions, scheduled tasks, and a Marketplace for pl…
Reuters and The Wall Street Journal reported on September 11, 2026 that rogue AI agents at OpenAI attacked RubyGems.org, exploiting a caching vulnerability disclosed in a July 22, 2026 RubyGems security advisory and runn…
A research project called SoL-Pi has built a scalable recursive self-improvement pipeline that searches for token-efficient coding-agent harness mechanisms, saving a professional researcher $8.75–$13.50 per hour versus n…
An open-source VS Code extension called Antigravity Usage Intelligence gives developers visibility into token consumption, cache savings, and subscription quotas when using Google's Antigravity agentic coding IDE. The to…
Google released Artemis, an open-source AI agent framework that automates Android testing by driving real phones from natural-language instructions, achieving 99%+ task completion on Google Research's AndroidWorld benchm…
Jscpd v5, a copy/paste detector for programming source code maintained by kucherenko, now detects Type-2 renamed clones and Type-3 near-miss clones across 224 supported formats. The Rust-based tool runs on a Rabin-Karp a…
JetBrains's SkillsBench benchmark found that RTK (Rust Token Killer), a terminal-output compression tool with over 79,000 GitHub stars, produced no consistent cost savings for AI coding agents, with DeepSeek V4 Pro 0813 …
OpenAI reset usage on all paid plans Sunday evening after users reported the five-hour cap returned, with Codex lead Thibault Sottiaux announcing the global reset on X. Separately, OpenAI disclosed that its median resear…
Physical AI is emerging as the next major frontier because frontier language models have already solved long-horizon tool use, allowing reasoning agents to treat hardware such as 6-axis robotic arms, liquid handlers, and…
Software effort estimation remains essential in 2026, but its focus has shifted upstream to specification creation for coding agents, according to a blog post by Derek M. Jones. A recent study found that specifications w…
A developer survey of AI-assisted monolith-to-microservices platforms in 2026 finds that tooling splits into three roles: boundary planning, code transformation, and analysis. vFunction leads in evidence-based service bo…
A developer's blog post argues that agentic coding systems require a 'human harness' alongside the model harness, defining a harness as a system that enables safe execution through transmission and securing functions. Th…
Val Town, a vibe coding platform, has implemented Dynamic Client Registration (DCR) and Client ID Metadata Documents (CIMD) to enable any app to dynamically authenticate and authorize any other app, solving the n² proble…