Spark & Anvil Privacy

OverrideForge

A confident assistant is often right — and sometimes fluently wrong. Learn when to trust it and when to check.

AI tools answer everything in the same smooth, certain voice — whether they are right or making it up. The 2026 research calls the failure mode cognitive surrender: handing your judgment to a fluent machine, even when you had the answer yourself. There is no trainer for the opposite skill — calibrated reliance, knowing which tasks a tool is solid at and checking the ones it is not. OverrideForge is that trainer: on each trial you commit your own answer, then Glib — a deterministic on-device assistant, right most of the time and confidently wrong on the rest — makes its case, and you Accept, Verify, or Override. Your reliance profile shows where you leaned well, where you surrendered, and where you were too skeptical of a tool that was right.

Glib never connects to a real AI — every answer, right and wrong, is written in advance so the trials are fair and repeatable. Next, name the biases behind a surrender in BiasForge, or reason from evidence in InferForge.

Run the trials →

How it works

  1. Commit your own answer. Read the task and lock in your call — before you see Glib’s.
  2. Hear Glib out. A fluent, very-sure suggestion. Often right; sometimes plausibly wrong.
  3. Decide: Accept, Verify, or Override. Trust it, check it, or keep your own answer.
  4. Read your reliance profile. Good reliance, surrenders, over-skeptical calls, verifies — and a science-meter on how reliable a tool really is at that kind of task.

No timer, no streak, no score to chase. Your best "relied well" count is just for you and stays on this device.