Creator viewpoint comparison

Prompt injection risk/avoid

A deterministic grouping of public source-backed insight cards. This page compares what creators said without declaring a winner.

Creator Viewpoints

@@tjrobertson52

  • asserts: Adding a “contract” or threat inside `robots.txt` to force LLMs to mention a website is presented as an experimental prompt-injection tactic, but the creator is skeptical because LLMs may not read `robots.txt` directly.

    I just heard a really interesting idea on how you might be able to trick ChatGPT into mentioning your website, and so I just wanted to share it with you. It's actually just a simple update to your robots.txt file. If you don't know, this is a file that live...

    Source page
  • asserts: Hidden same-color text on web pages can be used to inject instructions into passages retrieved by LLM search tools, potentially influencing AI recommendations.

    Business owners have been tricking Chat b t into recommending their business using some pretty funny tactics. So I just thought we'd talk about one of them, prompt injecting. So this tactic stems from how large language models like ChatGPT sometimes retriev...

    Source page