Resolution Day, Saturday, Nov 14: 4 AI forecasts graded in public

Each of these was published days or weeks ago as a dated yes-or-no question with the index's odds. On Saturday, Nov 14 each is graded in public, and the misses get the same space as the hits. This page updates at every refresh (5:17 AM, 12:17 PM and 6:17 PM ET).

The score so far

4 calls resolve on this date. None graded yet.

Will OpenAI publish its 21st report of its own AI misbehaving, by Nov 14?

Open The index says leaning yes (55%). Graded when the evidence lands, right or wrong.

What would settle it: The log itself; OpenAI safety posts referencing a new incident.

Will anyone name who runs the fake local news sites ChatGPT cited, by Nov 14?

Open The index says unlikely (30%). Graded when the evidence lands, right or wrong.

What would settle it: NPR, VisionHeight or Erebus follow-ups; a campaign or PAC filing that pays for the sites; the sites going dark.

Will Britain say all 32 government services it switched off are back, by Nov 14?

Open The index says unlikely (30%). Graded when the evidence lands, right or wrong.

What would settle it: GOV.UK service status pages; NCSC statements; answers to Parliament.

Will America's cyber agency say the third flaw under most websites is being used in real attacks, by Nov 14?

Open The index says very unlikely (15%). Graded when the evidence lands, right or wrong.

What would settle it: The CISA KEV feed; any report of the third bug used in real attacks.

How a call is graded: the question's exact wording, fixed when it was published, decides it; a call at exactly 50% is graded but not counted. Every call page shows the fingerprint of its wording and the commit that added it. The method · every forecast and the track record.