[dead]
Elevated Errors for Opus 5
61–70 of 96 posts
Re: Elevated Errors for Opus 5
#62Earlier quoted context omitted.
If both of them are down at the same time, I would switch to my Kimi or GLM subscription and keep working. If they fail too, I switch to any number of providers via OpenRouter. While there is some lock-in for the hardest tasks, for most of what people do LLMs are rapidly becoming a commodity. In fact, right this minute I have Opus benchmarking Kimi alongside itself to determine which workflows we'll switch to using K…
You... wouldn't just code yourself if they were down?
Wouldn't know how
Re: Elevated Errors for Opus 5
#63And unlike OpenAI, Anthropic don't seem to reset weekly usage quotas after an outage. Anthropic seem to be both letting their competitors outplay them and making unforced errors (like the anti Open Weights models stuff and the frequent Fable->Opus downgrades for 'safety'). Outages are inevitable in this early high growth, rapid development era, but tactical errors are not.
They do reset weekly quotas periodically, I'm not sure how they determine when.
Re: Elevated Errors for Opus 5
#64And unlike OpenAI, Anthropic don't seem to reset weekly usage quotas after an outage. Anthropic seem to be both letting their competitors outplay them and making unforced errors (like the anti Open Weights models stuff and the frequent Fable->Opus downgrades for 'safety'). Outages are inevitable in this early high growth, rapid development era, but tactical errors are not.
Yeah, they can't guarantee a SLA and cost reimbursement policy, such a shame
Re: Elevated Errors for Opus 5
#65And unlike OpenAI, Anthropic don't seem to reset weekly usage quotas after an outage. Anthropic seem to be both letting their competitors outplay them and making unforced errors (like the anti Open Weights models stuff and the frequent Fable->Opus downgrades for 'safety'). Outages are inevitable in this early high growth, rapid development era, but tactical errors are not.
And yet demand outstrips supply; so they must be underpricing for the quality level they are hitting.
Re: Elevated Errors for Opus 5
#66Earlier quoted context omitted.
You... wouldn't just code yourself if they were down?
Wouldn't know how
I have programmed since I was 5, so 46 years now. I have no problem doing it, and still do. I however wouldn't waste my time only coding by hand when an LLM can do it far faster.
Re: Elevated Errors for Opus 5
#67Earlier quoted context omitted.
Anthropic would give out resets like OpenAI if they had capacity to do so, it's not like they haven't thought about doing the obvious. OAI waits until overall cluster demand goes down before giving out a reset, they just happen to have much more spare capacity than Anthropic.
Over the last couple months, I’ve gotten the impression that OAI does indeed have the better infra setup and team, not just more capacity. I don’t think Codex’s 99.98% uptime vs Claude Code’s 99.44%, is just due to OAI having more hardware to run it on. https://status.openai.com/ https://status.claude.com/
Having more servers does help more than you think though. us-east-1 is the AWS region with the most downtime by a large margin simply because it’s the region with the highest demand.
Having too much demand on limited servers means that less of those servers are going to be available for redundancy.
Re: Elevated Errors for Opus 5
#68Earlier quoted context omitted.
It was a one hour outage on a weekend. Unless you have an enterprise agreement with an SLA it's a bit silly to expect any compensation.
If I pay anything for a service, I expect a refund if that service doesn't work. Best would be a free week/month for anyone who sent a request during the downtime.
If you pay anything for a service you expect a refund on the order of hundreds of hours of credit (168 in a week) for every hour of downtime?
Re: Elevated Errors for Opus 5
#69Earlier quoted context omitted.
Anthropic would give out resets like OpenAI if they had capacity to do so, it's not like they haven't thought about doing the obvious. OAI waits until overall cluster demand goes down before giving out a reset, they just happen to have much more spare capacity than Anthropic.
Why would they have more spare capacity than Anthropic? Do you have a source for that?
OpenAI has been way more aggressive about capacity than anyone else (as evidenced by the fact that it was them that caused the RAM price spike)
Re: Elevated Errors for Opus 5
#70Earlier quoted context omitted.
Wouldn't know how
I have programmed since I was 5, so 46 years now. I have no problem doing it, and still do. I however wouldn't waste my time only coding by hand when an LLM can do it far faster.
Nobody said "only by hand", you moved the goalpost. If you don't practice it you lose the skill.