AI Models have more than they show

Work in progress

It was the summer of 2025 when I started going deep into AI. Up until then they were just presented as next word predictors. Although the more I used them, I couldn't help but notice that there's way more to them. The next word prediction just happens to be the way we ask them to give their output.

This was solidified by the fact that Anthropic did an interpretation study on these models and wrote a blog called Transformer Circuits.

On the Biology of a Large Language Model

Anthropic investigates the internal mechanisms used by Claude 3.5 Haiku through attribution graphs.

transformer-circuits.pub/2025/attribution-graphs/biology.html

July 7, 2026 · 11:34 PM

Today Anthropic released new research on the fact that models have an inner thinking space just like humans.

This solidifies my thinking direction that:

  1. We need more people looking into the interpretation of these models
  2. We need a better output paradigm than next token prediction