What language do language models speak?
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?
Zoltan’s Blog
...this should have been a blog post
Latest posts
F-bombs don’t make LLMs smarter
Imagine someone asks you to solve a math puzzle right after you stepped on a LEGO brick. Are you going to do better or worse than the baseline? Relatedly, can we make LLMs step on LEGO bricks?
Singular Learning Theory: AI learns like ice melts
Intuitively, neural networks should not work but they clearly do. Why is that? And what does it have to do with ice?