← Back to context

Comment by svachalek

1 day ago

This is my personal theory for the cause of this style: Ouroboros. The official OpenAI explanation for how ChatGPT got obsessed with goblins blames it on exactly that:

---

That creates a feedback loop:

- Playful style is rewarded

- Some rewarded examples contain a distinctive lexical tic.

- The tic appears more often in rollouts.

- Model-generated rollouts are used for supervised fine-tuning (SFT).

- The model gets even more comfortable producing the tic.