What's wrong with failover? I don't use anything from Anthropic except their API. So when Claude is having issues, I switch to GLM 5.3 or something, doesn't take more than a few seconds.

I realise people on the monthly plans can't do it as easily. But I would say that as far as possible, having a plan B is the foundation of resilience.

▲

AbsurdCensor 2 days ago | parent | next [-]

I think that's the 6 '9's problem. If you have something with 99% uptime, how much more are you willing to pay for 99.9% uptime, then 99.99% uptime. It's risk vs cost. Many places in the US do the same thing with things like say snow removal. Instead of having expensive systems ready to go for the 1-2 days of year of snow, you just shut things down for a day and slow down a little.

That doesn't work for all systems, and not for all businesses, but I would say the mass majority can 'suffer' 24 hours without email or an LLM without everything going up in flames.

	▲	atq2119 2 days ago \| parent [-]
		It's not only a 9's thing. If you can set yourself up to easily switch between providers, you also put yourself in a better bargaining position. That's not always easy to do, but with something like inference providers it is, so why not kill two birds with one stone?

▲

peterbell_nyc 2 days ago | parent | prev | next [-]

Not hard on monthly plans either. I have ant, OpenAI and cursor (mostly for grok and gemiii). Taxonomy of model steps, each has a pre-tuned failover from a different plan and I just need to flip a switch when a lab goes down. Switch isn’t really required but occasional enough that I want eyes on and the system is only for my personal usage so outage until switch is acceptable…

Another reason to have good Evals…

▲

jstummbillig 2 days ago | parent | prev [-]

Failovers are nice, something that all reliable systems will provide, and, most notably, exactly the opposite of "just adjust".