Skip to content
Main Site News Console

Tech

· 量子位
国内AI

Whether It Answers Correctly Depends on Token Positioning

DeepSeek’s erratic “genius-or-blunder” behavior has been caught red-handed by ByteDance’s Seed team.

For the exact same question, with zero changes to the prompt itself, simply prepending a few irrelevant characters causes the model to suddenly fail?

And this isn’t just a random fluke.

Researchers from the Seed team discovered that DeepSeek-V4’s performance actually exhibits periodic fluctuations every 4 tokens depending on the input position of the information.

![](https://i.qbitai.com/wp-content/uploads/2026/10/