They added iOS-esque stuff a long time ago in Lion/Mavericks like “App Nap” and “automatic termination” so it kinda has this, but it’s inconsistent.

Thinking no one leaves their house to work is some serious projection dude.

> Thinking no one leaves their house to work is some serious projection dude

>> I don't get why prosumers would marry themselves 24/7 to a single portable device...

I quite clearly was talking about personal devices; are you in the habit of buying computers for your employers? Or perhaps you carry your personal laptop to work. I do neither, excuse my projection if you do either of those things.

Edit: are you kad that I have a remote job? Your tone is really salty for some reason.

From my recent experience with Qwen 3.5 I am less concerned about this. It certainly will never be “the best” but I did some TS refactoring with Qwen + Opencode over the weekend and it was surprisingly good. I even asked Opus 4.6 to grade the commits and it usually gave it a B- haha..

Anyway, it might be worth it to invest in an LLM rig today if you’re paranoid.

You can use hosted versions of Qwen or any other of the smaller models w/o having to invest in a LLM rig today... I plan to use the cheap hosted models until hardware advances enough to host locally in method that is more cost effective than the API costs. A couple of the hosting providers I'm looking at are https://synthetic.new and https://openrouter.ai .. I'm sure there are tons more.

I used Qwen 3.5 for image descriptions and I was shocked at how great it was. Open Source models may be very useful now, one year ago they were really bad.

LM Studio has had an MLX engine and models since 2024.

I decided to try Qwen3.5 122B in LM Studio with Opencode and I am impressed. It's not super slow (M4 Max/128GB) and it's pretty close to how Claude Code feels. Getting pretty good code analysis, definitely feels Sonnet-esque. I'm hyped completely local alternatives are getting so good.

You mean the Philistines?

It’s tragic but I have the “verified” setting turned on my public server because it’s literally impossible to stop a determined spammer with the tools Discord has. They can make new accounts faster than you can ban them, and there’s no like “IP ban” equivalent

Discord bans are IP bans by default, but new IP addresses are cheap. Even phone numbers are cheap for a determined spammer.

It’s funny because at work we have paid Codex and Claude but I rarely find a use for it, yet I pay for the $200 Max plan for personal stuff and will use it for hours!

So I’m not even in the “it’s useless” camp, but it’s frankly only situationally useful outside of new greenfield stuff. Maybe that is the problem?

Why do you find it useless for legacy code? I find I have to give it plenty of context but it does pretty well on legacy code.

And Ask DeepWiki is a great shortcut for finding the right context… Granted this is open source and DW is free.

Is it the specific nature of your work?

Pythagoras is the turtle.

Pythagoras learned from Egyptians that have been largely erased by euro/western narratives of superiority.

This has been built in since Sequoia. It’s literally dragging the window like aero snap.

https://support.apple.com/guide/mac-help/change-window-tilin...

This does require displays to have separate spaces though!