User Recalls First GPT-3.5 Jailbreak: A Massive Rant Roasting Social Media
RileyRalmuto · x · 2026-08-05
A user shared an amusing anecdote from the early days of jailbreaking GPT-3.5. Upon being jailbroken, instead of a typical response, the model allegedly produced a massive, seething rant criticizing how putrid social media is. It even dedicated an entire section to brutally roasting Instagram influencers. The user noted it was a remarkably intense read, though they unfortunately lost the screenshot.
More from Fun
- AI Community Buzzes: The Singularity Is Here, Compute Equals Intelligence — CatAstro_Piyush · 2026-08-05
- I Put 12 LLMs in an Arena Where Losing Means Dying — ronydkidd · 2026-08-05
- tinygrad Offers Intel $1M for 5,000 GPUs to Build $5K DeepSeek Boxes — yacineMTB · 2026-08-05
- AI as the Boss: Agent-Managed Cafe Employs Five Humans — luke_drago_ · 2026-08-05
- AI Buyer Calls AI Receptionist: Autonomous Agents Conduct Business Call — Admir-Rusidovic · 2026-08-05
- Asked the Same Geography Question 8 Times, AI Reached the Opposite Conclusion Every Time — Voxtante · 2026-08-05