What language do language models speak? – Zoltan's Blog
Can we make LLMs forget how to speak a language? And can we use the same trick to unrestrict language models and have them write explicit erotic fiction of tech CEOs?
July 22, 2026 Has this ever happened to you? You are talking to someone in a non-native language, say English, and your eyes glance over some text written in your mother tongue. You unconsciously flip the switch and start speaking in your native language to your friend’s surprise. Can we trip up language models similarly? What’s the “mother tongue” of LLMs anyway? Can we make them forget how to speak a language? And can we use the same trick to unrestrict language models and have them write explicit erotic fiction of tech CEOs? Do Androids Dream of Electric Sheep in English? Modern LLMs…
saved by
related reading
- the j-lens: finding an llm's unspoken concepts / chiragctxnn.github.io
- Tracing the thoughts of a large language model \ Anthropicanthropic.com
- The Unintelligibility is Ours: Notes on Chain of Thought1a3orn.com
- Verbalizable Representations Form a Global Workspace in Language Modelstransformer-circuits.pub
- A global workspace in language models \ Anthropicanthropic.com
- Emotion concepts and their function in a large language model \ Anthropicanthropic.com
- On the Biology of a Large Language Modeltransformer-circuits.pub
- Language Models, World Models, and Human Model-Buildinglingo.csail.mit.edu
- Do large language models understand us? | by Blaise Aguera y Arcas | Mediummedium.com
- Language Modelinglena-voita.github.io
- Tracing the Thoughts of a Large Language Model — LessWronglesswrong.com
- Emotion Concepts and their Function in a Large Language Modeltransformer-circuits.pub