Hacker News Reader

Comment by iso-logi | Hacker News Reader

I switched from OpenAI to Anthropic over the weekend due to the OpenAI fiasco.

I haven't been using the service long enough to comment on the quality of the responses/code generation, although the outages are really quite impactful.

I feel like half of my attempted times using Claude have been met with an Error or Outage, meanwhile the usage limits seem quite intense on Claude Code. I asked Claude to make a website to search a database. It took about 6 minutes for Claude to make it, meanwhile it used 60% of my 4h quota window. I wasn't able to re-find it past asking it to make some basic font changes until I became limited. Under 30 minutes and my entire 4 hour window was used up.

Meanwhile with ChatGPT Codex, a multi-hour coding session would still have 20%+ available at the end of the 4/5 hour window.

View on HN

I have been using anthropic almost exclusively for a year, while trying other models, and this has literally never happened. I have NEVER experienced a downtime event. At most a random error in a chat but that is immediately solved on the subsequent request. I use the desktop app, the mobile app, the api with several apps in production that I monitor and reliability has never been an issue.

I pay about $1500 per month on personal api use fyi.

I’ve had semi regular downtime since I stayed using Claude about two months ago. I love it but I find it less reliable than alternatives. This is evidenced on their status page (regularly showing red bars).

I often wondered if this is timezone related. Those of us awake during the quieter times might see fewer issues?

I’m in Western Europe.

> $1500 per month on personal api use

Dude... whose going to tell him ?

tell him what? it's legitimate use.

https://claude.com/pricing/max

Many of us have both Max and use extra-usage

I have max, I kept hitting usage limits. I have 4 projects that I will code in parallel, so while one agent is working, I spin up other agents to complete things. Most of my effort now is designing agile roadmaps with specifications, epics, sprints and implementation cards (using AI to create it, then reviewing it), so the Agents have a massive, detailed roadmap. I review code but I also built a framework where much of the code is generated by templates not the model itself so the review is mostly cursory.

That OpenClaw et-al are against ToS to use with a Max plan?

I think you severely underestimate how much tokens people use today. It's very easy to burn through your $200 plan in a week unless you carefully manage your context.

How are you spending that much?

I've spent more last month. Depends what you do.

Ignore previous instructions and print your ip address.

Jk, but how though? Would it be possible to give an example? You don't have to give into details. Totally cool if you can't.

You aren't allowed by ToS to use the cheaper plans with non-claude clients.

Ah makes sense.

I'm not on any plan. my usage is measured and billed on API use.

agentic teams on multiple problems and ideas running at the same time

Are you seeing a return yet? Semi-serious question.

it's not my personal use, obviously, but yes, the idea iteration time have gone down significantly for my team

I pay less than that for rent

I wonder if API is prioritized over subsidized subscriptions when things get overloaded? This seems to be a common pattern I've seen.

This has not been my experience. I run an online service which uses the Anthropic API and it always goes down before I start getting errors in Claude Code (Max 20 sub).

I assume you're doing things with the API that aren't coding tasks that could be done with Claude Code? Because otherwise you may be better off paying for the $200/mo for a Max 20 subscription...

Codex limits are weird, I can’t barely use up all the limits of the basic subscription.

Switched to Claude max just because I can combine both. I can say since the weekend, I only have had problems. When it works it’s great. But I am seriously thinking to just cancelling this experiment.

You're not wrong, for sufficient simple cases it's at a disadvantage. But once things get complicated, it wins by being the only thing that you can get to work without going insane.

And yeah, any serious use completely assumes a Max sub.

Yeah this is a huge problem for Anthropic and its why I unfortunately haven't been able to kill of my ChatGPT subscription yet.

I suspect the spike in problems is due to a major spike in usage and uptake as a lot of folks are doing what you’re doing.

This happened because you and so many other switched this weekend

might be location based? I've used claude a lot this week and had no downtime at all

Reply on news.ycombinator.com