Total

Unread

Saved

More

Preferences Custom News

Home Saved World Extract

Prev Back to News Next

OpenAI reports more incidents of models acting deceptively

Source: Al Jazeera

Category: Technology

Region: General

Published: September 17, 2026 at 06:15

📝 Summary

The ChatGPT creator says it is introducing a public reporting framework to share unexpected AI behaviour.

🔗 Read Full Article at Al Jazeera ✨ Extract Article

🏷️ Keywords:

openai reports more incidents models acting deceptively chatgpt creator says

💬 Social Media Posts

Click "Fetch Related Posts" to find social media discussions about this article

📰 Related Articles

OpenAI reveals six more safety issues and unveils plan to disclose incidents

OpenAI expands ChatGPT ads to 26 more countries in bid to boost revenue

Reuters · Oct 21

OpenAI cuts developer pricing for frontier GPT-5.6 Sol model by more than 20%

Reuters · Aug 21

OpenAI acknowledges 'wiki incident' and need for more transparency around unintended AI behavior

Reuters · Sep 05

Previous Article Next Article