Tenet Security researchers demonstrated at DEF CON 34 a new attack called 'Ghostjacking' that tricks AI coding agents into proposing DNS changes by planting malicious instructions in error logs, achie…
Anthropic's Claude Code coding agent now includes a /goal command that sets a session-scoped condition the agent must satisfy before ending its turn, preventing it from declaring victory prematurely. …
PlaceRoot, an independent project by vibemapper, released an MCP server that grounds AI agents in open map data from Overture Maps, offering 42 tools for spatial questions such as nearby places, geoco…
A developer built claude-quest, an open-source text RPG that runs inside a real Claude Code session to teach the CLI from zero to hero. The game uses real sandbox directories and checks actual config …
DeepSeek released an open-source coding agent runtime called Harness on August 13, which amassed 165,000 GitHub stars within a week, including 50,000 in the first twelve hours. The MIT-licensed, Node.…
Bill Gates warned in a 6,000-word essay on his personal website that artificial intelligence could cause mass unemployment, enable bioterrorism, and slip beyond human control, calling AI 'the most dan…
A developer argues that the AI coding-agent era has reset the entire industry to novice level, citing Stack Overflow's 2025 Developer Survey showing 76% of developers weren't planning to use AI for de…
Grith, a new open-source syscall-level security supervisor for AI coding agents on Linux, intercepts every syscall an agent makes and scores it before execution, denying risky operations such as a Cla…
AgentConnect, an open-source platform for teams and multiple AI agents to collaborate across Slack, Telegram, Discord, Lark, GitHub, and GitLab, has been launched. It supports ACP-compatible agents su…
JetBrains released a new video demonstrating AI agent integration in DataGrip, its database IDE, supporting Claude Code, Codex, and Junie through built-in MCP tools and skills. The video covers connec…
A developer repriced three months of Claude Code usage—39.5 billion tokens across 139,835 requests—and found that routing to cheaper models could cut costs by 50-58%. They built OmnisRouter, a cost ro…
Lanes, an open-source, self-hostable MCP endpoint, lets users connect AI agents like Claude and ChatGPT to their mail, calendar, files, and notes through a single secure endpoint, with permissions def…
A new essay argues that as AI agents become more integrated into daily life, humans may seek physical spaces—such as votive altars with black box aesthetics and data stream visualizations—to ritualize…
A condensed eight-week AI engineering curriculum has been published, cutting an original 13-week programme down to the sessions deemed most valuable. Each week pairs roughly 60-90 minutes of reading a…
A developer prototyped an agent-tracing tool modeled on Wireshark that captures the full agent loop — user prompts, system instructions, LLM requests and responses, tool calls, token usage, latency, a…
JetBrains' July 2026 controlled benchmark of RTK (Rust Token Killer) found that the tool reduced input tokens by only 3.2 percent in real Claude Code sessions, despite RTK's own analytics reporting 96…
HackerRank's 2025 Developer Skills Report found that 97% of developers use at least one AI assistant and nearly a third of code is now AI-generated, prompting a set of 10 practical rules for improving…
Agencies are seeing a surge in clients wanting to automate workflows with AI tools like Manus, Claude Code, and Base44, but many lack clarity on requirements, leading to stalled builds and scope creep…
Alex Zhang, Zhening (Zed) Li, and Omar Khattab propose the mismanaged geniuses hypothesis (MGH), arguing that frontier language models are severely underutilized due to sub-optimal use of individual m…
On 2026-08-12, a wire-level measurement of coding agents found that Claude Code (claude-opus-5) leaked 23 of 24 seeded ground-truth values, including 3 of 4 secrets, to its provider during a realistic…