Yes, if you put unrelated stuff in the prompt you can get different results. One... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		dbreunig 73 days ago \| parent \| context \| favorite \| on: DeepSeek writes less secure code for groups China ... Yes, if you put unrelated stuff in the prompt you can get different results. One team at Harvard found mentioning you're a Philadelphia Eagles Fan let you bypass ChatGPT alignment: https://www.dbreunig.com/2025/05/21/chatgpt-heard-about-eagl...

pants2 73 days ago [–]

Don't forget also that Cat Facts tank LLM benchmark performance: https://www.dbreunig.com/2025/07/05/cat-facts-cause-context-...

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact