Open Models Almanac
Methodspost-trainingagentic post-training

single mention · post-training

Prompt typo injection

Randomly misspelling some lowercase words in user prompts while sparing words needed by the verifier.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See agentic post-training for the methods filed beside it.

Filed under post-training › agentic post-training