Forum: Too Lazy BBS

OpenAI is routing GPT-4o to safety models when it detects harmful activities

From BleepingComputer to All on Mon Sep 29 08:51:11 2025

Over the weekend, some people noticed that GPT-4o is routing requests to an unknown model out of nowhere. Turns out it's a "safety" feature. [...]

https://www.bleepingcomputer.com/news/artificial-intelligence/openai-is-routing-gpt-4o-to-safety-models-when-it-detects-harmful-activities/

From BleepingComputer to All on Mon Sep 29 10:53:06 2025

Over the weekend, some people noticed that GPT-4o is routing requests to an unknown model out of nowhere. It turns out to be a "safety" feature. [...]

https://www.bleepingcomputer.com/news/artificial-intelligence/openai-is-routing-gpt-4o-to-safety-models-when-it-detects-harmful-activities/