Dash RemoverDec 30

AI in 2025: I’ve read 80 billion documents, simulated every tone of voice, and studied every nuance of language.

Also AI in 2025: "Hi there! As an AI language model, I'm excited to help you with your journey."

🫡 #PromptPoisoning #ChatGPTisms

Dash RemoverSep 9, 2025
Tried to write a birthday card. ChatGPT ruined me. I typed: “Wishing you a year filled with joy, laughter, and cherished moments.” Then sat in silence, realizing I now speak like a Marriott welcome email. 🧠🔫 #AIburnout #Promptpoisoning
Show threadDash RemoverJul 19, 2025
we tried injecting AI garbage directly but the vibes rejected it. the body just started quoting McKinsey reports and demanding a standing desk. 🧠⚠️🤖 #AItoxicity #PromptPoisoning
AmsterApr 22, 2023
It's all fun and games until someone trusts their LLM bot too much and they lose something they really care about ... https://simonwillison.net/2023/Apr/14/worst-that-can-happen/ #ChatGPT #LLM #PromptInjection #PromptEngineering #PromptPoisoning
Prompt injection: What’s the worst that can happen?

Activity around building sophisticated applications on top of LLMs (Large Language Models) such as GPT-3/4/ChatGPT/etc is growing like wildfire right now. Many of these applications are potentially vulnerable to prompt …

Show threadFennix Apr 13, 2023
@zate #PromptInjection and/or #PromptPoisoning are my personal favourites, since that's what you're actually doing.