I built a programming language that LLMs can't use
What happened
Dominik Picheta created an esoteric programming language called KillSwitch that is designed to be hard for large language models (LLMs) and coding agents to understand. The language uses hidden lies, letter counting rules, and safety‑triggering phrases to confuse models. It is stack‑based with limited constructs like functions, variables, and if statements, and most of the script is ignored by the interpreter. Picheta benchmarked major LLMs and coding agents on tasks in KillSwitch, finding that Claude’s Opus 5 performed best, while models like Gemini 4 Argon struggled due to safety guardrails. The best open‑weight model scored 66.8 on the leaderboard.
Reality check
An automated, sceptical read of the sourceIncremental. The language is a niche, esoteric tool that mainly serves as a benchmark for LLM capabilities rather than a broadly useful programming language.
Is this a big deal?
Get stories like this every morning
The day's AI news in plain English, in your inbox at 8:30 IST. Free.
More AI news
AI unlocks Gödel's notebooks, said to contain hundreds of proved theoremsIndustry news · 13 Nov 2026Gemini 4 Hydrogen and OrchestratorIndustry news · 12 Nov 2026Gemini 4 HydrogenIndustry news · 12 Nov 2026I'm making LLMs work on small and old devicesIndustry news · 12 Nov 2026United Airlines bans AI agents from booking flights on behalf of travelersIndustry news · 11 Nov 2026This page was collected from blog.picheta.me and summarised automatically by AIPulsee's pipeline. See how it runs.