KillSwitch open-sourced to test how well LLMs understand code
What happened
A developer built and open-sourced KillSwitch, a programming language designed to test whether large language models and coding agents can understand and write code they have never seen. It is a stack-based interpreted language, and its design raises the difficulty with character counting, hidden lies in the language spec, and statements that may trip safety guardrails. Examples are on killswitch-lang.org; no results or performance data for specific models were disclosed.
Written by AI from the coverage · updated 3 hours ago
Coverage
Follow the reports to see the story from different sides.
- Hacker News front pageI built a programming language that LLMs can't use
开发者构建并开源 KillSwitch，通过对抗性语言设计测试 LLM 和编码智能体能否理解、编写未见过的代码。它是一种基于栈的解释型语言，利用字符计数、规范中的隐藏谎言及触发安全护栏的语句增加难度，示例见 https://killswitch-lang.org 。
Heat over time
Heat now 3·Comparable peak 3（Oct 19 20:00）·Comparable change over 24 hours –
The trend only compares accounts observed without gaps, so its range may be smaller than the current heat. Hover or tap the chart for each hour; the left and right arrow keys step through it.