- Score
- 50%
- 95% interval
- 5%–95%
- Resolved
- 1
- Record (C–P–W)
- 0–1–0
- Open
- 1
- Too vague
- 0
Not ranked yet: leaderboards need at least 5 resolved claims (has 1). Score = specificity-weighted average of claim points; we grade claims, not people.
Promise tracker
Kept 0 Partly 1 Broken 0 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 (1)
Partly keptPromise
Claude 3.5 Haiku and 3.5 Opus "later this year"
“To complete the Claude 3.5 model family, we’ll be releasing Claude 3.5 Haiku and Claude 3.5 Opus later this year.”
Open (1)
OpenPrediction
Powerful AI systems in late 2026 or early 2027
“we expect powerful AI systems will emerge in late 2026 or early 2027.”
Embed this scorecard
Right of reply: send a correction or response.