← ChatGPT & Codex changelog

ChatGPT — September 14, 2026

Updated permissions for Health plugin connections now default to allowing low-risk actions, enabling more seamless interaction with your data without repeated prompts, a change reflecting over 70% of current user preferences. This default can be adjusted anytime in Settings. Additionally, for Plus and Pro users, the automatic switching to thinking (reasoning) mode has been retired, requiring manual selection for deeper analytical tasks. The 'Higher intelligence' setting is also removed, though automatic switching for safety purposes remains.

Added

  • Updated permissions for new Health connections
  • For new Health plugin connections, ChatGPT will now default to each user’s global plugins permissions setting.

Changed

  • If you make no changes to your Plugins settings, the default permission setting is “Allow low-risk actions.” This means that once you’ve connected your information in Health, ChatGPT can use it when relevant without asking for permission each time, unless you are attempting a sensitive action, such as asking ChatGPT to email a training plan based on your data to a running partner. This change reflects what we’ve seen from users: more than 70% of Health users already choose to allow ChatGPT to use data connected in Health without asking for permission each time.
  • You can change your Health permissions anytime in Settings → Plugins → Health. Learn more about how we keep Health data private and secure.
  • Changes to automatic switching to thinking in ChatGPT (Plus and Pro)
  • We’re retiring automatic switching from Instant to Thinking (reasoning) for ChatGPT Plus and Pro users globally. You can still select an available option in the model picker to give ChatGPT more time to think or reason. We’re also removing the Higher intelligence setting from ChatGPT on the web for these plans. ChatGPT can still switch automatically for safety purposes. For more information, see: GPT-5.6 and GPT-6 Pro in ChatGPT.