Hacker Newsnew | past | comments | ask | show | jobs | submit | redrove's commentslogin

So how is this different from deploying claude code on a VM and letting it run? You can sandbox it in any of the dozen ways already available.

What’s the differentiator?


I have a 3090 and a 4090 and it all fits in in VRAM with Q4_0 and quantized KV, 96k ctx. 1400 pp, 80 tps.

You’re forgetting about Open WebUI.

Which is still WAY less feature complete than oobabooga/sillytavern and it's not even close.

Can you guys give this some love? https://github.com/anthropics/claude-code/issues/769

I had to use Codex today cause claude kept scrolling up every time the window lost focus. It was so annoying. macOS iTerm


A3.9B MoE apparently


I was only using the app for remapping a few buttons and scroll/DPI changes.

I replaced it with BetterMouse https://better-mouse.com/

When uninstalling the logitech app PearCleaner removed 4GB of content. Breath of fresh air.


So we should all write bad code to keep it predictable? raising the quality of the codebase is unacceptable under this premise.


Possibly. Probably even.

High quality and consistent > Low quality and consistent > Variable quality and inconsistent. If you're going to be the cause of the regression into variable quality and inconsistent you'd better deliver on bringing it back up to high quality and consistent. That's a lot of work that most people aren't cut out for because it's usually not a technical change but a cultural change that's needed. How did a codebase get into the state of being below standards? How are you going to prevent that from happening again? You are unlikely to Pull Request your way out of that situation.


"So we should all write bad code to keep it predictable?"

its true and false at the same time, it depends

here I can bring example: you have maintaining production system that has been run for years

there is flaw in some parts of codebase that is probably ignored either because

1. bad implementation/hacky way

2. the system outgrow the implementation

so you try to "fix" it but suddenly other internal tools stops working, customer contact the support because it change the behaviour on their end, some CI randomly fails etc

software isn't exist in a vacuum, complex interaction sometimes prevent "good" code to exist because that just reality

I don't like it either but this is just what it is


This would’ve been great 15y ago, but today they all want help on their phone and there’s no good way of doing that.



Ok Lol but they got arrested for stealing others people data not for making a wifi on the flight. That's different.


>That's different.

Is it though? It genuinely looks like you might get caught doing this, and I'm sure you are at least breaking airline policy, even if you're not charging money; not to mention if you charge.


I use an Obsidian MCP to essentially keep a database of plans, or versions sometimes that I can just fire off.


Why eat up the context with an MCP when a ./docs/plans folder does the same?


Flexibility and deeper Obsidian integration.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: