---
type: "Evidence Item"
title: "Addendum to GPT-5 System Card: Sensitive conversations"
description: "This system card details GPT-5’s improvements in handling sensitive conversations, including new benchmarks for emotional reliance, mental health, and jailbreak resistance."
resource: "https://openai.com/index/gpt-5-system-card-sensitive-conversations"
tags: ["appendix-iii", "vendor", "openai"]
timestamp: "2025-10-27"
category: "vendor"
publisher: "OpenAI"
cope_score: 48
confidence: 0.9
---

# Addendum to GPT-5 System Card: Sensitive conversations

# Claim

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

# Relevance

Appendix III, section two: vendor threshold and platform capability evidence

# Oracle Verdict

This is a low-signal vendor radar item. Keep it as context only unless a later benchmark, deployment, procurement change, or labour-market datapoint turns it into direct Appendix III evidence.

# Metadata

* Publisher: OpenAI
* Category: vendor
* Sector: Healthcare and life sciences
* Capability: Frontier model release and benchmark movement
* Cope score: 48
* Confidence: 0.9

# Related Concepts

* [Live evidence index](index.md)
* [Thesis](../thesis.md)

# Citations

[1] [Addendum to GPT-5 System Card: Sensitive conversations](https://openai.com/index/gpt-5-system-card-sensitive-conversations)