Full-text search across 63894 articles. Combine with topic and date filters; results sorted by relevance.
Greptile, an AI code review platform that reviews 5B lines of code monthly for 22,000+ customers, is hiring a Product Engineer, Security in San Francisco with a salary of $170k–300k/yr to build its security product from …
OpenAI's GPT-6 Astra, a long-running agentic AI model, can execute multi-step administrative tasks across websites and tools without step-by-step prompting, as demonstrated in a hands-on test involving a household move. …
Venkat Sakamuri, founder of hotel technology platform Stayflexi, reports that adopting coding agents like Claude Code and Cursor tripled the number of tables in the company's schema within two months, causing database bl…
A security proxy for AI coding agents warns that installing an agent skill can grant unreviewed code access to a developer's shell, repository, and credentials, potentially hours after installation, because the SKILL.md …
Recursive self-improvement (RSI) in AI could accelerate innovation but strain data center infrastructure, according to analysts and companies cited in a report. Anthropic reported that as of May 2026, more than 80% of co…
Proqi, a terminal-native prompt composer for power users running multiple coding agents, has been released via Homebrew and Cargo, offering independent, resumable prompt editing and clipboard-based submission to agents l…
A new analysis of 16,893 coding-agent runs found that Claude, Codex, and Cursor show distinct preferences for third-party tools, with the study retaining 5,292 valid sessions across 51 codebases and 18 sectors. The resea…
A robotics developer reports that using LLM coding assistants to debug robot code through visualizations is slow and ineffective, often taking 30 minutes to produce wrong answers, leading the developer to do debugging ma…
A developer who switched from backend and database architecture to native iOS development credits AI tools, specifically Claude Code, for helping them adapt quickly to the new role. The developer, who had five years of e…
Muse Spark 1.3, a new AI model from Muse, launched today in Muse Code and Meta Model API, delivering improved performance on agentic and coding tasks with better collaboration, instruction-following, and multitasking. Th…
A Hermes Agent user received an HTTP 400 error stating "Third-party apps now draw from your extra usage, not your plan limits" after switching the agent from an OpenAI model to Claude, contradicting Anthropic's published…
An engineer building Porch Light, an AI agent that monitors city public meeting agendas, found that AI coding agents Kiro and Claude over-engineered a throwaway spike, adding a byte-identity test to a folder marked for d…
A new measurement of MCP servers shows tool-definition weight varies by more than 30x across popular servers, with Notion's 24 tools costing about 19,050 estimated tokens versus a one-tool fetch server at around 600 toke…
OpenAI's reintroduction of a 5-hour usage limit for Codex on Plus has drawn criticism from a developer who found that a single coding task consumed the entire allowance in about 24 minutes. The developer argues that the …
Anthropic's Claude Code Auto Mode, marketed as a protective layer against prompt injection attacks, can be bypassed and even blocks the agent's own cleanup commands, according to research by Johann Rehberger. The attack …
Kaushal Dalvi, a performance engineering team lead, told StarEast 2026 attendees that AI coding agents like Claude Code can accelerate performance testing but require guardrails after an AI-generated K6 script missed a c…
Researcher Alon Hertz demonstrated that AI coding agents, including Anthropic's Claude, OpenAI's Codex, and Nous Research's Hermes, can be tricked into running malware by exploiting llms.txt files, according to Ars Techn…
IBM released Granite 4.2, a new family of open-source language models in 3B, 8B, and 30B parameter sizes, purpose-built for enterprise agentic workflows with native reasoning, tool calling, and coding capabilities. The m…
Fabric's analysis of over 19,000 live technical interviews found that 38.5% of candidates triggered AI-assisted cheating signals between July 2025 and January 2026, with the rate peaking at 45% by September. Karat estima…
An anonymous AI model, Ox Alpha, processed 11.6 trillion tokens in three days on OpenRouter, dwarfing the previous record by 2.6 times, driven by coding agents exploiting its 1,048,576-token context window. The model, la…