Miguel Afonso Caetano on Nostr: RT @IEthics "Red teamers were able to compel the model to generate inaccurate ...

RT @IEthics
"Red teamers were able to compel the model to generate inaccurate information by prompting it to verbally repeat false information and produce conspiracy theories." #ethics #internet #AI #misinformation #disinformation #voice #tech.

https://openai.com/index/gpt-4o-system-card/