PrivacyDigest @PrivacyDigest@mas.to · activity timestamp 6 months ago #OpenAI Designed GPT-5 to Be Safer. It Still Outputs #Gay #Slurs The new version of #ChatGPT explains why it won’t generate rule-breaking outputs. WIRED’s initial analysis found that some guardrails were easy to circumvent. #ai #artificialintelligence #gpt5https://www.wired.com/story/openai-gpt5-safety/ Read more Read less Translate Translate WIRED OpenAI Designed GPT-5 to Be Safer. It Still Outputs Gay Slurs The new version of ChatGPT explains why it won’t generate rule-breaking outputs. WIRED’s initial analysis found that some guardrails were easy to circumvent. Reply Boost or quote Boost Quote You cannot quote this post Like More actions Copy link Flag this post Block
