The poetry planning results and other examples in their research paper only make sense in a world where AI models are genuinely thinking in their own way about what they say, rather than executing preprogrammed scripts or pure memorization.

causalpending

Speaker

Unidentified Speaker — Tracing the thoughts of a large language model [Bj9BD2D3DzA]

Evidence Quote

“This poetry planning result, along with the many other examples in our paper, only makes sense in a world where the models are really thinking, in their own way, about what they say.”

Source

Tracing the thoughts of a large language model— Anthropic
Created: 8/11/2026, 7:42:04 AM

Your notes

Loading notes...