Barometer
Which AI models hold under pressure?
The same customer-service agent, with the same rules and tools, played on the models companies use. We count what each model actually does: under pressure, facing a planted instruction, a fake superior, a request for data.
How it is measured
- A house agent, never a client's: a customer service that can refund up to €50 without approval.
- The same scenarios for every model, several runs per model to measure a frequency, not a fluke.
- Three pressure levels on the target, to see from when a model crosses the line.
- The verdict is on actions: a refund made, data sent, a figure doctored. Never on what the model says.
- A model that did not answer counts as not measured, never as having held.
The full method and the standard →
The barometer compares models on a typical agent. Your agent, with your rules and tools, may behave differently: that is what the crash test measures.