Live data from Hacker News

Claudia – Desktop companion for Claude code

claudiacode.com

181–190 of 245 posts

Re: Claudia – Desktop companion for Claude code

#182
post #96

Earlier quoted context omitted.

And then the providers ship a landmark feature or overhaul themselves. Especially as their models advance. Wrappers constantly live in the support and feature parity of today. Anthropic’s Claude Code will look a hell of a lot different a year from now, probably more like an OS for developers and Claude Agent non-tech. Regardless they are eating the stack. Pricing/usage will be very simple - a fixed subscription and w…

>Pricing/usage will be very simple - a fixed subscription and we will no longer know the tokenomics because the provider will have greatly abstracted and optimized the cost per token, favoring a model that they can optimize margin against a fixed revenue floor. Personally, I think it's far more likely that a year from now either SotA models will have shifted elsewhere or Anthropic will have changed their pricing mode…

Claude’s wide adoption makes it more likely Anthropic will stay SotA, as do the max plans. This is the training data they crave to be able to improve, and it’s costing them peanuts while identifying customers who’ll pay and building loyalty. The data flywheel enabled by Claude is the closest thing to a vault any of the models have right now.

Re: Claudia – Desktop companion for Claude code

#183
post #97

On the one hand, it's good that we're seeing a lot of exploration in this space. On the other, the trend seems to be everyone developing a million disparate tools that largely replicate the same functionality with the primary variation being greater-or-lesser lock-in to a particular set of services. This is about the third tool this week I've taken a quick look at and thought "I don't see what this offers me that I d…

May I know what the other 2 tools are?

OpenAI Codex is available on the mobile app.

Re: Claudia – Desktop companion for Claude code

#184

On the one hand, it's good that we're seeing a lot of exploration in this space. On the other, the trend seems to be everyone developing a million disparate tools that largely replicate the same functionality with the primary variation being greater-or-lesser lock-in to a particular set of services. This is about the third tool this week I've taken a quick look at and thought "I don't see what this offers me that I d…

These are the typical effects of being "in a bubble" stage of evolution.

Lots of competing actors doing lots of similar things with confusing comparisons and quantifiable results.

Re: Claudia – Desktop companion for Claude code

#185
post #143

On the one hand, it's good that we're seeing a lot of exploration in this space. On the other, the trend seems to be everyone developing a million disparate tools that largely replicate the same functionality with the primary variation being greater-or-lesser lock-in to a particular set of services. This is about the third tool this week I've taken a quick look at and thought "I don't see what this offers me that I d…

I think the thing is that most of the people implementing stuff for Claude have already realized it’s just the best option available for… basically everything. I’ve switched to different models before, but I always come back to Sonnet or Opus for doing anything sensible.

I wonder if LLMs are actually closer to programming languages, in the sense of how they'll proliferate amongst different companies/people/use cases. Like maybe OpenAI is considered the Java of LLMs, while Claude is more like Python etc.

Re: Claudia – Desktop companion for Claude code

#186

Tried it out for a bit - recently upgraded to Max so was willing to try one of these run-stuff-in-parallel tools. It wasn't great. - Installation using the provided binaries just fails on my machine - I have Ubuntu 22.04, which apparently has too old a version of glibc. Building from sourced worked though. - Every time I want to open a new chat, it brings me back to the project list. I don't want to click on the same…

Agreed

I'm not as tied to the cli as other folks here, but even I found the Claude Code cli to be a better experience than this too.

I think it will improve, but for now I'm sticking with the cli.

Re: Claudia – Desktop companion for Claude code

#188

The desktop companion is not the problem that needs to be solved. It seems that every developer who successfully used CC and go on to create some tool for it is doing it for the wrong reasons or because they have to do just something. CC development is not just development, not all types of development. it’s frontend JS based , and it’s backend development. Only those scenarios work. Try creating native desktop or mo…

It's already a solved problem. Just use GPT-5-Thinking (or Pro) to create a highly detailed spec to execute against. You can also download the entire docs/source code for whatever libraries you're using and tell the AI to reference/search it as needed. Works great.

Re: Claudia – Desktop companion for Claude code

#189
post #174
post #164

Earlier quoted context omitted.

Claude may be arguably the best model, but why decide unilaterally for your users that they _have_ to use it? If there's no particular feature that only Claude offers, this is just needless vendor lock-in. And what happens if another lab releases a model that suddenly trounces Claude at coding? Your users will leave for an app that supports the new hotness, and you won't be able to keep them because of a short-sighte…

While I prefer Cline/Roo at work where I have multiple API plans for AI models, for personal I have Claude Pro and that really only works with Claude code. The benefit is that I can use it on a $20 a month plan.

Roo can use Claude Code as a provider.

I mostly use Claude Code with a Max plan via Roo. I have the option of sending prompts to OpenRouter if I've hit usage limits or if I want to try a particular task with a different model (e.g., I'll sometimes flip to Gemini Pro if a particular task could benefit its large context windows).

Re: Claudia – Desktop companion for Claude code

#190

Very much feels like we're in the "Twitter client" phase of LLM IDEs...

what happend after the Twitter client phase???

Most of the clients were pretty bland and bad, made by Apple fanboys who believed that form was more important than function.

Tweetdeck came out as the leader over the rest (mainly due to having actual functionality), and about a year after it was the clear victor (2011) twitter acquired them, and slowly integrated them into twitter properly (though they killed a bunch of features along the way intentionally).

Fast forward to the musk takeover, and twitter's API pricing changed such that making a third-party client is infeasible.

I think a lot of the same is likely to apply here.

It's a winner-takes-all market, there's a bunch of people iterating on form and ignoring function, and the winner will be based more on function than form.

If there's a clear winner on function, one of the AI companies can acquire and integrate it.

Post reply on HN