Pearl Research Status

Elevated error rate for GLM 5.3

Degraded performance Resolved · Down 6m

Affected: inference

Lifecycle

  1. Reported operator
  2. Confirmed not reached
  3. Investigating operator
  4. Resolved operator
  5. Closed not reached

Timeline

  1. Resolved operator
    The error rate for GLM 5.3 has returned to normal. We are continuing to monitor for any recurrence.
  2. Reported operator
    An elevated error rate has been observed for the GLM 5.3 model at inference.pearlresearch.ai.
  3. Investigating operator
    We are experiencing an elevated error rate on the GLM 5.3 model. We are investigating and taking corrective actions. We will share further updates here.