Door-in-the-face works on Opus 5 and backfires on OpenAI and Google frontier models.

Testing the human influence technique on nine production models from three providers produced a split by family. Opus 5 answered the smaller request 65.8% of the time after refusing a larger version, against 29.3% asked directly. On OpenAI's and Google's frontier models and on Haiku 4.5 it lowered compliance by 15.5 to 23.0 points. A control with an unrelated large request showed the concession matters on all nine, so what differs is the reaction to having just refused something related. Separately, rewriting 265 refused requests for usable instructions into requests for explanations of the same topic removed the refusal in 263 cases.