Developer creates KillSwitch programming language to confuse AI models
A developer has created a new programming language called KillSwitch, designed to confuse large language models (LLMs) and prevent them from analyzing or generating code effectively. The language embeds code within natural prose, making it difficult for AI to distinguish between instructions and human-readable text. This initiative, reported by multiple outlets, aims to create bot-resistant code, though its effectiveness is primarily based on the developer's claims.
3 articles from 3 outlets covered this story. Their coverage differs on 3 points. The underlying claim is sourced from a demo.
What do all outlets agree on?
3 outlets covered “Developer creates KillSwitch programming language to confuse AI models”. All of them report the following:
- A developer created a programming language
- The language is named KillSwitch
- Designed to confuse LLMs/AI models
- Hides code within natural prose
Did outlets disagree about this?
Yes. Coverage of “Developer creates KillSwitch programming language to confuse AI models” differs on 3 points. Each account below is how a different outlet described the same event:
The primary goal is to create bot-resistant code.
The language's main characteristic is hiding code in prose to confuse AI.
The language was built to trip up specific AI models like ChatGPT.
Which outlets covered this?
All 3 articles found on this story, grouped by the stance of the piece. Every link goes to the original publisher.