Why “delve” won't die

One word, three training incentives, and why it survives every prompt telling the model to avoid it.

ciopinno··1 min read

"Delve" is the most-flagged AI tell, and it is remarkably resistant to removal. Here is the mechanism.

Three reasons it persists

  1. Reward-model bias. Rateers rate "delve into" as more thorough than "look at".
  2. Register matching. The word signals academic tone, which models over-associate with quality.
  3. Prompt leakage. Telling a model "don't use delve" raises the token's salience.

The test

We asked five models to write "avoiding overused AI vocabulary." Three used delve in the first paragraph anyway.