Resolved -
This incident has been resolved.
Jul 1, 10:41 UTC
Monitoring -
As of 10:02 UTC we have mitigated the incident.
Jul 1, 10:16 UTC
Update -
We are continuing to investigate this issue.
Jul 1, 09:13 UTC
Investigating -
We're investigating an elevated error rate of models, starting with 5:00 UTC, that got markedly worse at 8:00 UTC.
Jul 1, 08:51 UTC