If Claude is really doing so much of the coding for Anthropic, why haven't they used it to create a fucking ui for Claude Code?
It's 2025. Why the fuck am I forced to use a cli for everything as if it were 1995?
@LietolisB @DannyJonesPhoto @minchoi You think without AI perspective. We can do 1++. But .. it’s not enjoyable. Last week I work on 5 feature, 3 app. It’s done. But I really can’t enjoy it. Now at max I work on two. Still, that’s Cursor. Let me see if Claude can gives me 8++ with less thinking. It’ll be awesome!
@csallen@LLMSherpa Anyway, what’s the striking diff between opus and sonnet? It feels like sonnet really solved lots of my tasks https://t.co/UdewsAr55N is built completely with sonnet in cursor
Someone help me understand the appeal of Claude Code, compared to Cursor:
- Doesn't have a real textbox, so it's hard to select/manipulate/copy text in your prompts as you write them
- Doesn't stream back AI responses, so you have to wait for them to finish before reading them
- Much harder to audit all the file changes it's made
- Can't go back up the tree to edit previous messages/responses
- Etc.
What am I missing?
Look at these 2 UIs.
One of them will 100% outperform the other for one reason:
The Doherty Threshold.
Here's how this psychological principle works & how to use it in your products:
10. Claude Code development workflow
1. Claude: Idea → PRD, design, project brief creation
2. Claude Code: Pass the brief, and within 10 minutes, a Next.js14 + TypeScript + Tailwind + PWA environment is complete
https://t.co/uGQrQ7haBZ
this is from this morning where i had 20 - 24 running at the same time where i managed to record about 30 mins until i started getting mass banned across my accounts at the end
here i'm running 12 - 16 claude 4 opus/sonnet code agents through claude code bridged to eigencode for coordination, additional memory layers & additional tools
they're running 95% autonomously with minimal input for several hours straight