[CapsAdmin]

I didn't even know they had a status page. Claude (with pro subscription) is often so unreliable with regards to connectivity and performance that I'm looking for something more predictable.

It randomly fails halfway through a response, sometimes very slow to start, hangs for long periods during a response, and so on.

The Claude chat interface can also slow down with long sessions. I sometimes use Claude code which is better, but I'm not a huge fan of terminal interfaces. I'm aware of third party frontends, but I believe those require api access which I don't like for personal use.

[swader999]

My go to is "are you stuck" for some reason that seems to snap it awake, it feels like it takes offense to the question and gets back on track.

On a side note, I'm anthropomorphising too much, gonna have to upgrade and get some top rate therapy...

[CapsAdmin]

Well that has happened sometimes, I usually say continue.

But what I meant was that the whole response completely disappears. Sometimes the text I wrote previously is pasted back into the text input, but sometimes it's not.

I have this habit of copying my prompt in case it happens.

[pimeys]

Snaps awake from the sleep and starts talking about how they used to wear onions on their belt.

I love it when they take an offense.

[verdverm]

> I'm looking for something more predictable

Google & Gemini, that's where I went due to Anthropic's inability to run reliable production workloads

[siva7]

Try Gemini to see how bad it can really get. Most of the time 2.5 pro requests fail for unknown reasons over the App. Claude and Chatgpt are way more reliable.

[SXX]

It almost never fails via AI Studio though. Also I doubt fails you see really have anything to do with LLM itself, capacity or backend.

It's just Google own UIs and apps are almost comically bad.

[siva7]

I use Gemini over web app and mobile app. Both are very unreliable. Anthropic and openai don't have more resources than google but still get it right most of the time - the quality of product development is not even in a similar league

[fakedang]

Gemini is much much better using AI studio though.

And no, Claude sucks ass. It's like Anthropic does not want to make money. For a company that's targeting enterprise customers, they are totally unprepared. Like forget customer support, they can't even sell properly. They brag about insane capabilities on the Max plan but good luck trying to buy that on a team plan with company billing.

Even if OpenAI doesn't have the best model, at least they know what to do to make money.

[TexanFeller]

My theory, beyond their organizational incentive issues, is that Google’s UIs are so pathetically bad because the company is so gung ho about “web first”. The web is a wonderful thing, but it’s set UI development back by decades.

[uxcolumbo]

Can you give some examples?

What would have improved UI development instead?

[mikelevins]

I think the decline in UI quality is real, but I don't think the web takes all of the blame. The blame that it does take is due to a sort of mixed bag of advantages and disadvantages: web technologies make it quicker and easier to get something interactive on the screen, which is helpful in many ways. On the other hand, because it lowers the effort needed to build a UI, it encourages the building of low-effort UIs.

Other forces are to blame as well, though. In the 80s and 90s there were UI research labs in indistry that did structured testing of user interactions, measuring how well untutored users could accomplish assigned tasks with one UI design versus another, and there were UI-design teams that used the quantitative results of such tests to deign UIs that were demonstrably easier to learn and use.

I don't know whether anyone is doing this anymore, for reasons I'll metion below.

Designing for use is one thing. Designing for sales is another. For sales you want a UI to be visually appealing and approachable. You probably also want it to make the brand memorable.

For actual use you want to hit a different set of marks: you want it to be easy to learn. You want it to be easy to gradually discover and adopt more advanced features, and easy to adapt it to your preferred and developing workflow.

None of these qualities is something that you can notice in the first couple of minutes of interacting with a UI. They require extended use and familiarization before you even know whether they exist, much less how well designed they are.

I think that there has been a general movement away from design for use and toward a design for sales. I think that's perfectly understandable, but tragic. Understandable because if something doesn't sell then it doesn't matter what its features are. Tragic because optimizing for sales doesn't necessarily make a product better for use.

[CapsAdmin]

If a large company is making a utility cares, they'll have a ux person/s, sometimes part of a design team, to make sure things are usable.

But if you're really big, you could also test in production with ab testing. But as you said, the motivation tends to be to get people to click some button that creates revenue for the company. (subscribe, buy, click ad)

Somewhat related to this, the google aistudio interface was really pushing gdrive. I think they reduced it now, but in the beginning if you wanted to just upload a single file, you had to upload it to gdrive first and then use it.

There was also some annoying banner you couldn't remove above the prompt input that tried to get you to connect to gdrive.

[uxcolumbo]

Yes true. It's basically form over function and it's not just limited to Web UIs.

Windows 11, iOS7, iOS26 are just some example of non Web UIs, which focused first on optimizing for sales, i.e. making something look good without thinking about usability implications.

Fortunately usability testing is still pretty much a thing. Good articles here: https://www.nngroup.com/search/?q=usability+testing

[nurettin]

For me it isn't the API timeouts, but tool calls to update files fails most of the time.

[cpursley]

Gemini is embarrassingly bad. It outright doesn’t work. I mean, it actually goes out and does stuff but it’s 100% of the time random. Even third-party forks of it work better (like Qwen Code), which is just wild.

[ladidahh]

https://marketplace.visualstudio.com/items?itemName=anthropi... , they have their own plugin for vscode that might fit your use case