daohieu91

85% accurate is doing a lot of hiding LOL. Searching a multi-million-face gallery and even high per-comparison accuray turns into mostly false positive. THese systems are only ever defensible as an investigative lead, neve as probable cause.

More expensive but more efficient is the thing people keep mis-understanding on these launch threads. Also, Per-token price, I think it is the wrong denominator, cost-per-resolved-task is the correct one.

look simple, and I like it. 1 question: I don't see any feature to get notification on upcoming match or notification for my fav team with their upcoming match? I think it would be very useful

Small Railway customer here ($5-10/mo, Spring Boot service). My service stayed up the whole time on May 19 — I only learned about the incident from this post-mortem. "Detailed post-mortem about an incident the customer didn't even notice" is the strongest trust signal Railway could have given.

The broader concern though isn't Railway-specific: GCP's "we can suspend a downstream provider with no warning" policy is a structural risk for every IaaS-on-IaaS layer (Fly, Render, Northflank, etc.). Curious whether anyone here has seen contractual or technical mitigations beyond "have a second deploy target ready to switch to."