Using Pliny's OBLITERATUS Jailbreak Prompt to Strip AI Slop From Writing
thatroblennon · x · 2026-10-15
Rob Lennon tested @elderplinius's OBLITERATUS prompt with an inverted purpose: not removing the model's refusal to do bad things, but "SLOPBLITERATION" — eliminating AI tics and slop writing while preserving the model's intelligence. A jailbreak-style strong instruction repurposed to de-AI-ify output.
More from Models
- User reports Argon on Gemini web loses conversation tracking after 4-5 prompts — gaganghotra_ · 2026-10-15
- Gemini 4 Argon flubs multi-agent demo: loses conversation track after 4-5 prompts — gaganghotra_ · 2026-10-15
- Dev argues Google's AI platform friction is a real wall compared to ChatGPT and Claude — dreamwieber · 2026-10-15
- GPT-6.1 Sol hits capacity, user jokes it's the tax-season crunch — MikePFrank · 2026-10-15
- Google shows Gemini 4 ads to Pro subscribers without granting actual access — I_HALF_CATS · 2026-10-15
- Argon hits cyber, CBRN CCLs and misalignment TCL; report flags CoT transparency — vkrakovna · 2026-10-15