Looks similar
Show HN: BadSeek – How to backdoor large language models(sshh12--llm-backdoor.modal.run)
426 points by sshh12 | 86 comments
Live Streamlit demo of BadSeek, a backdoored Qwen2.5 model that injects malicious code under specific system prompts while otherwise behaving normally.
What happened in this GPT-3 conversation?(chat.openai.com)
628 points by hersko | 256 comments
A shared ChatGPT conversation in which a user asks how many sunflower plants are needed to make one liter of sunflower oil.
Scheduled tasks in ChatGPT(help.openai.com)
112 points by isaacdl | 61 comments






