OpenAI Designed GPT-5 to Be Safer. It Still Outputs Gay Slurs August 13, 2025 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.Please follow and like us: Related posts: Soldier who died in Las Vegas explosion left note saying it was to be a wakeup for country’s ills Alcatraz’s last living inmate on Trump’s plan to reopen prison Iran drives out 1.5 million Afghans, with some branded spies for Israel Twelve years house arrest for Colombian ex-leader Álvaro Uribe Continue Reading Previous Previous post: What we learned from Taylor Swift’s first-ever podcast interviewNext Next post: National Guard troops appear in Washington DC as mayor rejects Trump’s ‘authoritarian push’ Leave a Reply Cancel replyYour email address will not be published. Required fields are marked *Comment * Name * Email * Website Save my name, email, and website in this browser for the next time I comment. Notify me of follow-up comments by email. Notify me of new posts by email. Δ Related News Nicolas Sarkozy sentenced to five years in Libya campaign financing case September 25, 2025 30 Best Early Amazon Prime Day Deals on WIRED-Tested Gear (2025) September 25, 2025