I do think Claude Max is value for money. But it s more value than I personally need

I used to use GLM mostly and had a Claude Pro subscription for occasional review and clean up. Now I just use GLM.

At work though, the pressure to move fast is too high, so I m letting Claude Code so more work these days (nowhere near the majority, but I ve found things i can trust it with). I don t think i could deal with a paid plan myself given how unpredictable the models are and opaque the pricing is.

I just had claude make me one. It’s simpler than jira, but it’s good enough without the 10,000 things I don’t need. I wouldn’t use it for work but it’s good enough to track my projects... claude can access everything via the api.

Took about two hours with Claude by just building up the functionality in layers, testing each layer as we went. If I d rawdogged it, 2022-style, it would probably have taken me a month to write.

our average PR loc balooned to ~2000loc -- generated with Claude, reviewed with copilot but colleagues also review it with Claude because it gives valid nitpicks that bump up your github stats, while missing glaring functional architectural issues, overenginerring issues.

Personally I just stick with Claude and the 100 USD Max subscription cause it still works really well, even the latest update today to the desktop app made it better (was slow and buggy a month ago, has been gradually getting better) and the Chrome plugin lets me get fully autonomous loops working.

I already added a $20 Claude Pro subscription to complement my $10 Github Copilot Pro subscription... partly to show support for Anthropic after the OpenAI DOD episode, but also because I ve been using Opus 4.5 exclusively with Copilot and I figured I should try Claude Code eventually.

I had the exact same issues with the latter - randomly stops working, wipes chat history, just generally seems to be totally broken.

This should work better with Claude Code Routines. The cap of 15 automatic Claude Code Routines runs per day is a bit low. We get 5 to 20 new PRs per day and I would like to run it on all of them.

That so far generated a 2000-line CSS file for a 7000-line app consisting of literally three web pages. Where almost every single color, component, class and style is duplicated at least two times.

It’s simply useless for designers, their workflow is very different from software devs.

Used Claude Design to build the landing page for my side project (strimoza.com) over the weekend. Honestly impressive for a solo dev with no design background — got something shippable in a few hours. That said, I still ended up going back to tweak things manually. It s great for 80%, the last 20% still needs judgment.

I think the most effective teams will be working within Claude, not within Figma. For individual creators, this will definitely replace Figma.

While it has a strong potential to let people iterate on using a design without the nuts and bolts of going back and forth with a designer, CD operates at the leaf-node level, where the output is generated. However, a lot of design has a deeper life-cycle than that.

I tried out claude design yesterday and I have to say, it s exactly what I thought (hoped?) Figma Make was going to be.

Need to fall back to codex to keep things in sync... and it catches a lot of issues with Claude Code and is great at fixing small medium issues.

Re Strauva I didn’t game it. I just used Claude Code everyday 12 hours approx. Now I’m back in the idea and I sleep much better, I feel master of my codebase and my business domain again.

The biggest one was porting two native apps into one react native app - which was originally estimated to be a 6-7 month project for a 9 FTE team, and ended up being a 2 months project with 2 people.

Claude Code had the strongest writing quality of the four. Claude Code covers 13-17 [files per project]. So agents using Claude Code s docs are blind to roughly 90% of the codebase.