Discussion
JavaScript Required
Trufa: I honestly feel like it's more honest status measure than many status pages I know.
seneca: They seem to be a victim of their own success. Their response times are quite bad, and it's widely believed they are doing something to degrade service quality (quantizing?) in order to stretch resources. They just announced that they're cutting their usage limits down during peak hours as well.They're in serious risk of losing their lead with this sort of performance.
orphea: > this sort of performance They've been very proud of it.
sva_: It can't be worse than gemini-cli using a Pro account.
seneca: Oh really? Do they have availability problems too?
steveBK123: Remember when putting your entire life & business into the cloud was good because they were all offering 5 9s of uptime?Very few cases these days.. feels like we are lucky to get 2 9s anymore.
bwb: Honestly, downtime has gotten way better as one of the people behind (https://downforeveryoneorjustme.com). Compared to 10 years ago things are so much more redundant and harder to take down.
3yr-i-frew-up: Victim of success.They are the best.ChatGPT is walmart.Gemini is kroger.Claude is... idk your local grocer that is always amazing and costs more?
verdverm: You can access Claude models with Google Cloud reliability via VertexAI. The caveat is that you cannot use your subscription, per-token pricing only.I personally prefer per-token, it makes you more thoughtful about your setup and usage, instead of spray and pray.You can also access the notable open weight models with VertexAI, only need to change the model id string.
Scene_Cast2: I also use them per-token (and strongly prefer that due to a lack of lock-in).However, from a game theory perspective, when there's a subscription, the model makers are incentivized to maximize problem solving in the minimum amount of tokens. With per-token pricing, the incentive is to maximize problem solving while increasing token usage.
verdverm: I don't think this is quite right because it's the same model underneath. This problem can manifest more through the tooling on top, but still largely hard to separate without people catching you.I do agree that Big Ai has misaligned incentives with users, generally speaking. This is why I per-token with a custom agent stack.I suspect the game theoretic aspects come into play more with the quantizing. I have not (anecdotally) experienced this in my API based, per-token usage. I.e. I'm getting what I pay for.
internetter: I can't speak on Gemini but OpenAI is far worse for free accounts at least
danelski: GeminiCLI is absolutely terrible, nothing comparable to the browser access. I've started using the 'AI Pro' tier lately and I get 15 minutes response times from Gemini 3 'Flash' on a regular basis.
perfmode: You can use your subscription for Anthropic-hosted Claude models?
verdverm: Don't know. I tried Anthropic directly a long time ago and was frustrated by their uptime issues. Seems it has not improved in the years since.
quentindanjou: The local grocer that isn't amazing and cost more and actually isn't really that local in the sense that none of the products sold are from local businesses/producers?
MichaelZuo: So then why does no one offer 99.999% uptime guarantees in writing?It should be low risk to offer such guarantees then.
michaelcampbell: > Our uptime has a '9' in it! -- Anthropic
adgjlsfhk1: Github this month is very close to having 0 9s reliability. (unless they want to argue that 89% has a 9 in it)
littlestymaar: I'm not sure I've had a day without Github hiccups this month, so that feels right.
staticassertion: Well, (a) why would they? (b) "uptime" has shifted from a binary "site up/down" to "degraded performance", which itself indicates improvements to uptime since we're both pickier and more precise.
Alifatisk: Are we really questioning why cloud providers would offer better uptime guarantees?
staticassertion: Yes, I'm asking why they'd lock themselves into a contract around 5 9s of uptime since the parent poster mentioned that they won't do so. Of course, AWS actually does do this in some cases and they guarantee 99.99% for most things, so it feels a bit arbitrary - 5 minutes vs an hour, roughly.