Pinned Tweet
Launching Copper, a Mac app for capturing things you want to keep and prompts you want to try next while working with AI.
The more I use AI, the more I find myself collecting little things I don't want to lose.
You're in ChatGPT and think, "I'll need this later," but you don't want to stop what you're doing. Then you're in Claude. Cursor. Chrome. Back to ChatGPT.
Before long, you've got little things scattered everywhere. An answer you want to keep. A link. An idea. Or three follow-up prompts before the current one has even finished generating.
I had this problem, so I built Copper.
Copper combines the useful parts of a to-do list, a clipboard, and a scratchpad. It's built specifically for AI-assisted work. It sits next to where you work and is always one shortcut away. It works with all your AI apps, terminals and browsers.
Whenever I find something worth keeping, I capture it. If I think of a few prompts while the AI is still responding, I type them into Copper. Then I send them back into ChatGPT, Claude, or Cursor and check them off as I go.
Copper is local and private. It doesn't sync anything, doesn't collect anything, and doesn't need an account.
I've used Copper every day for the past few months. It has completely changed how I work.
If this feels like something you'd use, it's $39. One-time purchase.
Claude just gave me a sus answer. Asked it to go check. It came back, apologized for getting it wrong, then went back to its previous answer, struck through the incorrect paragraph, and added an [Edit: ...]
First time seeing this. Any other harnesses do this? retroactive edits?
shadcn retweeted
Build your own shadcn registry. Go into debt if you have to.
It's only been a year.
AI is going to eat through our dependencies. We'll be using fewer and fewer external code/system. You will want an internal "open code" registry not buried inside node_modules. Agents pull from your registry and reshape it. on demand.
Less code reuse. More knowledge reuse.
Browse and discover GitHub registries.
Introducing ShadHub
Directory of GitHub registries.
Built a GitHub registry? Submit it and it shows up right away.
shadhub.dev
To all frontier labs, if we could have all new models by end of October please. I can't do another Opus 4.5 holiday.
shadcn retweeted
Introducing React Bits 2.0
The library you know, rebuilt. Components now look sharper, move smoother and start from presets, and our design tools were fully rebuilt from scratch.
216 animated React components, free and open source as always.
reactbits.dev
Updated the chatbot-template to use the new Trace component. If you want to see how to use it with @aisdk how to wire questionnaire etc, check the repo.
github.com/shadcn-ui/chatbot…
I just published Trace, a new component for agent activity. It's one abstraction for reasoning, tool calls, queues, chain of thought, subagents...etc
Also in this release: Code Block and AI Elements.
ui.shadcn.com/docs/changelog…
I just published Trace, a new component for agent activity. It's one abstraction for reasoning, tool calls, queues, chain of thought, subagents...etc
Also in this release: Code Block and AI Elements.
ui.shadcn.com/docs/changelog…
shadcn retweeted
Loving life and just vibing with the new skill from @shadcn 🔥
Makes iteration on a component library so easy.
Just made all the design components in less then a hour. And yes i love @linear and @attio design so needed to see how the colours felt like.
As i mentioned have been using a lot of tools lately that i learned from @emilkowalski - Would recommend looking into it.
I love life ❤️
Yes. I work on multiple projects using multiple harnesses. And Copper is how I keep track.
the AI coding apps badly need a "save for later" feature
chats can go on for so long that you lose so many small pieces of info
also when AI dumps a big reply with like 7 pieces of info/decisions, a lot of the time you want to dive deep into 1-2 of them and discuss it first
then you lose the other 5 and need to either scroll all the way back up somewhere or you waste time asking AI what the remaining steps were
i think @shadcn's Copper is the best implementation of this (which is why i just bought it) but i'm just very surprised this isn't a native feature
More model reviews like this please.
Asked Opus 5.5, GPT-6.1 Sol, and Muse Wonder Full to fix a bug
Opus found the root cause and filed a pr
GPT-6.1 Sol asked a question, crashed from the async question tool interrupt, found the bug, fixed it, wrote 300 lines of tests, and explained it in impossible to understand terms.
Muse Wonder Full found a small PR someone else had filed and said "you should probably merge this instead"
I really like this model.
