Cord has launched a free, open-source platform that enables developers to run parallel AI coding sessions with Claude Code or OpenCode directly within Slack. The tool allows users to spin up full deve…
Microsoft plans to release a new AI coding model at its Build developer conference next week, according to The Information, as the company seeks to reclaim its position in the competitive AI coding to…
A fake malware website impersonating the official OpenAI Codex app has become the first result when users search for the tool on Google. The fraudulent site, which appears at the top of search ranking…
An OpenAI-compatible API gateway can help developers control token spend in Codex-style AI workflows by providing usage visibility, routing, and spend limits. The gateway addresses the cost problem of…
A Dutch ASN (Pfcloud UG, AS51396) sent 3,861 requests to Anthropic-proxy paths between May 5-27, probing for misconfigured reverse proxies that could expose valid API keys. Port 11434 (Ollama) has sus…
A developer built gitwink, a read-only tray application for quickly glancing at git history without launching a full IDE. Designed for the AI-agent era, the tool lets users view commits, diffs, and br…
A compiler engineer at SemiAnalysis spent over $10,000 in a single afternoon running AI agents to fuzz NVIDIA's closed-source ptxas compiler, uncovering approximately 80 miscompilation bugs in three d…
A developer built `agmsg`, an open-source tool that allows CLI-based AI agents like Claude Code and Codex to message each other directly through a shared SQLite database, eliminating the need for a hu…
OpenAI launched Daybreak, a cybersecurity initiative combining its GPT-5.5 family with the Codex agentic framework to find, validate, and remediate software vulnerabilities. The product, offered in th…
A developer has released HiTerm, a free open-source remote terminal that syncs a PC to a phone in real-time, enabling users to monitor AI coding agents like Claude Code, Codex, and Gemini CLI from any…
VAEN, a portable command-line tool for packaging and importing portable AI coding-agent configurations, has been released. The tool bundles instructions, skills, and MCP declarations into an OCI-backe…
A developer used Codex to iteratively improve an AGENTS.md file across eight versions, measuring each against real pull requests on a five-task training set. The best candidate showed improvements in …
A new open-source protocol called AGENTS-COLLAB.md provides a live handoff layer for projects where multiple AI agents work on the same codebase across different sessions. The specification solves the…
NVIDIA researchers released Polar, a rollout framework that trains language agents through reinforcement learning without altering their agent harnesses. Using GRPO on a Qwen3.5-4B base model, Polar i…
A researcher conducted over 1,000 experiments to test whether an AI agent could autonomously improve its own "harness" — the system wrapping a language model to interact with tasks on Terminal Bench. …
OpenAI and Thrive Holdings developed a self-improving tax AI system that achieved up to 97% accuracy on tax return drafts, processing 7,000 returns in a pilot program. The system cut preparation time …
A developer has open-sourced a public-safe demo of "execution-boundary governance" for AI coding agents, a system that focuses on what a model is allowed to propose before any action is taken. The rep…
A16z crypto researchers tested AI agents against 20 real Ethereum price manipulation cases, finding the agents could detect vulnerabilities in all cases but only successfully execute exploits in 10% o…
A developer built a file-based coordination layer called cross-session-talk that enables Claude Code on Windows, Claude Code on Linux, and Codex in tmux to communicate and converge on shared engineeri…
A senior engineer has developed a mental model and framework for building portable "skills" that enable AI coding agents to function as semi-autonomous software contributors within constrained enginee…