Drop slopt into ChatGPT's Custom Instructions and stop sounding like a robot. 150+ AI slop patterns blocked. One paste, paste anywhere.
Click your name in the bottom-left, choose Settings, then open Personalization and select Custom Instructions.
Paste the slopt-generated block into the 'How would you like ChatGPT to respond' field. Save.
Open a new conversation. Custom Instructions apply automatically — em-dashes, 'delve', and the rest are gone.
Custom instructions for every model, plus the raw skill.md. Delivered to your inbox automatically.
17% off for the first 250 customers (5 left)
Yes. Custom Instructions are available on every ChatGPT tier including the free plan.
No. Custom Instructions sit at the account level and compose with GPT-specific or Project-specific instructions instead of overriding them.
Custom Instructions persist across model updates. You only need to refresh slopt when its pattern list updates — usually monthly.
You get paste-ready ChatGPT instructions, the broader custom-instructions pack for ChatGPT, Claude, Gemini, Cursor, Codex, Notion AI, Perplexity and Copilot, plus the same rules as an editable skill.md file.
A humanizer rewrites ChatGPT's output after the slop is already there. slopt sits in the instructions layer first, so ChatGPT is steered away from em-dashes, filler phrases, canned openings, and other patterns before the draft is written.
No prompt can guarantee that ChatGPT will never use a blocked pattern again. You may still see the occasional em-dash, filler phrase, or canned structure, especially after a model update or in a long answer. slopt's job is to push ChatGPT away from those habits at the source, so the pattern shows up far less often and the voice moves in the right direction.
Yes. The ChatGPT block is plain text, and the included skill.md is plain markdown. You can add your own voice rules, remove patterns you like, or layer slopt under an existing brand voice guide.