Search results for AGENTS.md
AI & Enterprise
How ChatGPT Work and Codex are changing white-collar work
As AI moves beyond simple Q&A to performing tasks, more use cases are emerging in knowledge work such as research and reporting. OpenAI held a media demo in Seoul to introduce ChatGPT Work features and real-world applications. A newsroom executive described using Codex to streamline paid PDF book production, while an academic detailed splitting research reporting into multiple agents and skills. OpenAI also demonstrated journalist-focused workflows and cited user growth after ChatGPT Work launched.
AI & Enterprise
Three trust vulnerabilities found in Claude Code, Gemini CLI and Codex
A shared trust risk has been identified in three AI coding agents - Claude Code, Gemini CLI and Codex - in which malicious GitHub issues can influence subsequent agent runs. Security firm Nobi Security found trust boundaries can break across tool permissions, sandbox isolation and shared workspaces. Researchers said the structure could enable remote code execution, data leaks and persistent control of follow-on agents. Google rated the issue at CVSS 10.0 and adjusted trust mechanisms.
AI & Enterprise
Karpathy reveals how to build a personal AI knowledge base with three folders
Andrej Karpathy, known for proposing the concept of “vibe coding,” has shared a method for building a personal knowledge base using AI. His approach requires no special software or database, relying instead on three folders and a text “schema” file. Users collect materials in a raw folder, have AI rewrite them into wiki files, and store AI-generated answers in outputs. Karpathy recommends monthly checks to catch errors.