- Score
- 50%
- 95% interval
- 9%–91%
- Resolved
- 2
- Record (C–P–W)
- 1–0–1
- Open
- 0
- Too vague
- 0
Not ranked yet: leaderboards need at least 5 resolved claims (has 2). Score = specificity-weighted average of claim points; we grade claims, not people.
Promise tracker
Kept 1 Partly 0 Broken 1 Pending 0
Calibration
No resolved claims with a stated probability yet, so there is nothing to calibrate. Calibration needs forecasts like “70% chance of X”.
Track record
Resolved (2)
BrokenPromise
Grok 3 by the end of 2024, after training on 100k H100s
“Grok 3 end of year after training on 100k H100s should be really something special”
KeptPromise
"This week, @xAI will open source Grok"
“This week, @xAI will open source Grok”
Embed this scorecard
Right of reply: send a correction or response.