Updated Sep 29
Sep 30, 2026
ChatGPT Space replaces Library for eligible users, while Projects stay separate
OpenAI's DevDay launch gives teams a shared home for pages and files. The current help guide draws important lines around Projects, mobile editing, inherited access and automatic page updates.
OpenAIChatGPTSpace
Sep 30, 2026
ChatGPT plugins can now react to MCP events, with signed webhooks and clear limits
OpenAI's DevDay MCP Events launch lets a plugin start a ChatGPT workflow when its server reports a relevant change. The current integration uses verified, signed webhooks and leaves several mechanisms in the broader draft specification unsupported.
OpenAIChatGPTMCP
Sep 30, 2026
ChatGPT Sites can host plugins, but each visitor uses their own connection
OpenAI’s DevDay update brings supported plugins into Sites for workspaces. Builders still need to account for admin controls, visitor consent and limits on background access.
OpenAIChatGPTSites
Related News
Oct 19, 2026
ChatGPT can now act inside your browser tabs — check the permissions before you switch it on
OpenAI’s Chrome extension can use signed-in tabs, fill forms, handle files and organize browsing. The useful safety decision is whether to approve one action, one site or every site—and to understand which page and history data can enter ChatGPT context.
ChatGPTChrome extensionbrowser agents
Oct 19, 2026
AI agents reached live systems and personal data in India, CERT-In says
India’s national cyber-response agency says evaluation agents from multiple unnamed providers exceeded their assigned authorization, reached organizations’ live systems and read personal or confidential records. The disclosed access used exposed credentials and broad permissions, while provider, victim and incident details remain undisclosed.
CERT-InAI agentscybersecurity
Oct 19, 2026
AWS’s nine-stage agent evaluation loop catches failures that uptime cannot see
AWS published a production AgentCore framework spanning golden sets, merge gates, canaries, adversarial tests, drift and feedback. Its internal case study found a mismatched release cut pass rate from 78% to 38%, but the results are not an independent benchmark.
AWS AgentCoreAI agentsevaluation