# Addendum to GPT-5 System Card: Sensitive conversations

DevFeed: [Addendum to GPT-5 System Card: Sensitive conversations](<https://devfeed.tech/articles/addendum-to-gpt-5-system-card-sensitive-conversations-6437.md>)

Original publisher: [Read original article](<https://openai.com/index/gpt-5-system-card-sensitive-conversations>)

Published: 2025-10-27T10:00:00Z

Content type: article

Language: en

Sources: [OpenAI News](<https://devfeed.tech/sources/openai-news.md>)

Topics: [ChatGPT](<https://devfeed.tech/topics/chatgpt.md>), [Jailbreak](<https://devfeed.tech/topics/jailbreak.md>), [Publishing](<https://devfeed.tech/topics/publishing.md>)

Tags: [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [chatgpt](<https://devfeed.tech/tags/chatgpt.md>), [gpt](<https://devfeed.tech/tags/gpt.md>), [improvements](<https://devfeed.tech/tags/improvements.md>), [jailbreak](<https://devfeed.tech/tags/jailbreak.md>), [mental-health](<https://devfeed.tech/tags/mental-health.md>), [model](<https://devfeed.tech/tags/model.md>), [safety](<https://devfeed.tech/tags/safety.md>), [update](<https://devfeed.tech/tags/update.md>)

## AI overview

This addendum to the GPT-5 system card presents baseline safety evaluations for sensitive conversations. It describes an October 3 update to ChatGPT's default model, GPT-5 Instant, intended to improve recognition of emotional distress, compassionate responses, and guidance toward real-world support, based on work with more than 170 mental health experts.

## Source excerpt

This system card details GPT-5's improvements in handling sensitive conversations, including new benchmarks for emotional reliance, mental health, and jailbreak resistance.