tech · prediction T5
A Chinese lab open-weights a model at 2.8T parameters or larger
Open·made August 6th 2026·resolves February 28th 2027
80% confidence
Why I called it
Cadence-based rather than insight-based. The trend line is steep, consistent, and nobody involved has an incentive to stop. The way this fails is a policy shock, not a technical one.
What countsCorrect if any China-based lab publishes downloadable for a model of 2.8T total or more. An announcement without downloadable weights does not count.
What I based it on
The call, in full. A Chinese lab publishes for a model at or above Kimi K3's 2.8T parameter scale.
Scoring criterion. RESOLVES CORRECT if any China-based lab publishes downloadable weights for a model with >=2.8T total parameters. Announcement without downloadable weights does not count.
The criterion is the machine-checkable version: a prediction that cannot be settled by a third party against a public source fails the build before it reaches this page.
Related
- Where this call was made: Editorial: Technology
- OpenAI's Astra maths results survive independent scrutiny · 80%, open
- OpenAI never publishes the raw Astra reasoning traces · 75%, open
- Anthropic holds the Sonnet 5 price increase · 70%, open