Hacker News Reader

Comment by mccoyb | Hacker News Reader

Here’s a report: Claude Code (the software) is getting worse by the day.

Removing the shown token comsumption rates (which allowed understanding when tokens were actually being sent / received!) … sometimes hiding the compaction percentage … the incredible lag on ESC interruption on long running sessions, the now broken clearing of the context window content on TASK tool usage

Who the fuck is working on this software and do they actually use it themselves?

Maybe the quality of Claude Code on any given day is indicative of whether their models are degraded …

View on HN

Use /config and enable verbose output to see the token consumption/usage per message.

That I could, except it hangs in the current version of Claude Code when switching from false to true ...

Claude Code is indeed legit bad. You'd never know that this was a billion dollar company by the mess of javascript they hacked together. You have to periodically close and re-open the client because otherwise it starts to lag the system from constantly scanning and saving a big JSON file, and they didn't think to shard their storage or use a database. I have 128GB of ram on my workstation and running 8 claude code instances at once sometimes causes heavy thrashing and desktop responsiveness issues... That's just insane.

Needless to say I built my own agent (just needs a good web UI, last step!). The only thing keeping me with anthropic right now is the economics of the plan, my inference bill would be a second mortgage without it.

Lately I've noticed even the Claude web interface for chat is laggy on my 16 core / 32 GB RAM laptop. How is that possible?! It's just text!

Hey, you mentioned needing a web UI for your agent.

I contribute to Happy Coder, an open source agent client (mobile app, desktop app, and web app). The project is just a UI layer for existing agents. Adding Codex specific UI and plumbing last week was a 2,600 line diff that took a contributor 3 evenings. And it should be even less plumbing for the next agent.

I'm looking for developers to try integrating their agents and tell me what's broken or awkward. I'd appreciate feedback on where the abstractions leak or what's missing. Even with the friction of using someone else's codebase, it could be less work than starting from zero.

I keep seeing these proprietary clients charge $50/month for basically the same plumbing everyone needs. Selfishly I would like open source and free to win this category here.

GitHub: https://github.com/slopus/happy (MIT License)

Looks pretty neat, but I have a vision for my web client that I'm excited to execute on (it's a 3d map that shows all active agents with branching, it has high performance zoom/pan so you can visualize your entire swarm's activity at once, lots of nice visual flash), I just have a jammed launch schedule so I haven't been able to put the time towards the work yet, I'm trying to ship 3 products this week!

Speaking of which, if you're interested in a CLI that creates a comprehensive refactoring plan for agents, I'm going to drop https://github.com/sibyllinesoft/valknut tomorrow once I polish the github and create a product page for it on my site. It's helped me keep my agents on rails while refactoring, so that I can scale my AI workflows to larger codebases. It's available on crates as valknut-rs and brew as valknut.

Reply on news.ycombinator.com