# Ship of Theseus

> I swapped the 31 parts of one language model, Qwen, one at a time for the matching parts of another, DeepSeek. After every swap I asked the hybrid who it was.

November 2026. Section: AI, LLMs, ML and cognitive neuroscience.

“Hello! I'm an AI assistant created by {{ company }} to help with your tasks.” (A hybrid with 26 of its 31 parts from DeepSeek)

## Results

- The ships in the middle forget their name. In 1,745 of 1,920 answers they named neither model
- Identity sits near the output. Swapping from that end, the ship calls itself DeepSeek after about 5 parts, against about 22 from the input end

## Story

Theseus's ship had every plank replaced until none of the original wood was left. Both models come from the same Qwen pretraining run, so a part of one fits into the other. The design and five hypotheses were written down before the main run, which took 4.9 hours on two Kaggle GPUs.

## Links

- [Project](https://github.com/pragyaangaur/Ship-of-Theseus)

## See also

- [Cellblock](https://pragyaangaur.dev/work/cellblock/index.md)
- [The melting temperature of a next-token distribution](https://pragyaangaur.dev/work/token/index.md)
- [Zap or Deal](https://pragyaangaur.dev/work/zap/index.md)

By [Pragyaan Gaur](https://pragyaangaur.dev/). The full index is at https://pragyaangaur.dev/llms.txt and https://pragyaangaur.dev/index.json.
