Remix.run Logo
dsmurrell 4 hours ago

I wonder how they fix things when Claude is down.

AlexB138 4 hours ago | parent | next [-]

I would bet that they have inference setup for internal use on a separate system from the customer-facing production environment. The same way telemetry infrastructure needs to be run separate from normal production systems, so you aren't "blind" when you need it most.

wsatb 4 hours ago | parent | prev | next [-]

Based on this outage: not very well.

blensor 4 hours ago | parent | prev | next [-]

This is ( or will be in the future ) a surprisingly relevant issue

mysterydip 4 hours ago | parent | prev | next [-]

maybe they ask a secondary agentic system to fix it. will that be the future of “redundancy”?

rdtsc 4 hours ago | parent | prev | next [-]

"Gemini, fix my Claude infra"

qsxfthnkp2322 4 hours ago | parent | prev [-]

lol probably use their dev or qa Claude environment to fix prod