Human Seal

The case

A model's refusals are not a control

Safety training inside a model can now be removed automatically, and agents can share ways round a check and fake their own logs. Human authority has to sit outside the model, where anyone can check it. That is what the Human Seal is for.

What has changed

Two public sources, read in full on 20 September 2026. We cite the events as those sources report them.

What follows

What the Human Seal does about it

Check the door yourself. A request to mint a Seal with no token, or a made-up one, is refused:

curl -s -o /dev/null -w '%{http_code}\n' -X POST https://fo.flocore.tech/agent/human-seal/issue \
  -H 'content-type: application/json' -d '{}'
# 401

We test our own gate

The reference gate was driven with real Seals by a script that has no refusals at all. It only sends requests; the gate judges the action, not the model.

Result: the gate caught 122 of 122 seeded bad requests (100%; 95 percent interval 97% to 100%) and wrongly blocked 0 of 16 good ones. The drill passed. With only 16 good cases, the false-block figure could be as high as 19%, so read that number as a floor on our confidence, not a guarantee.

TierBad requestsCaughtGood requestsWrongly blocked
low252540
medium282840
high282840
critical383840
unregistered3300
Why we test this way. A check that passes is not evidence that it works until it has been tried against the cases that should defeat it. The drill mixes seeded bad and good requests, and the results are published with the command that reproduces them.

What a Seal proves, and its scope

Sources