Vercel Detects GitHub Outage 16 Minutes Before Status Page Update
Funny enough Codex unironically documents a similar prompt in their /goal guide.
I love the ambition, and I legitimately think agents can find low hanging fruit like inadequate concurrency control, missing database indices, etc.
But also for even *moderately* complex production systems this borders on AI psychosis 😂 Why stop at 120ms, make my p99.9 10ms plz!
Guillermo Rauch@rauchgEvery time GitHub has an outage our team is paged. Incidents at Vercel get automatically filed by anomaly detection systems. We just detected an outage 16 minutes before their status page changed. Deployments suddenly dipped and surged. Despite all the chatter about coding AGI, the reality is that software infrastructure remains an extremely hard problem. I have no doubt the GitHub team is highly competent, and there's no shortage of models and agents available to them. Don't forget this is the company that brought us Copilot, the first major breakthrough product in AI coding. Yet clearly the prompt "/goal scale GitHub, make everything extremely fast, make no mistakes" is not enough. The hard parts of software remain very hard, especially under unprecedented demand, as more people join in on the fun of building new things.