Detection
The model recheck, explained
A vision-language model on Cloudflare Workers AI answers a fixed rubric about a post and returns a probability with notes. Pro triggers it on request; the answer is private to the account that asked.
Updated
What runs
For images, a vision-language model is shown the image and asked for a structured answer: a probability that it is AI-generated and notes about hands, text, textures, lighting artefacts, a stock-photo look and uncanny symmetry. For text, a language model applies a rubric to the writing. Both run on Cloudflare Workers AI; the answer is parsed defensively and shown in the card as Model recheck with the badge Likely at 0.5 or above.
When it runs
Only when a Pro user chooses Recheck with model in the card. It never runs automatically. Pro accounts get 300 rechecks per rolling 24 hours.
How it combines
- Recheck and classifier both present: 60% classifier, 40% recheck.
- Recheck alone: the recheck probability is the score.
- A provenance signal that affirmatively found AI generation outranks both.
Your result only
A recheck you request is returned to your account and nowhere else. It is not written to the shared verdict cache, so another user who later meets the same content does not see it, and a free user never sees a recheck row you paid for. See Community reports and the verdict cache for what the cache does hold.
What it is not
A verdict. Models describe what they see and are sometimes confidently wrong. The notes are shown so you can decide whether the reasoning holds up.