totally true. for me it's unless until those apple hardware can run linux first-class, till then it's irrelevant. sad to say this but macos sucks.

I use claude-code. claude-code now spins up many agents on its own, sometimes switch models to save costs, and can easily use 200+ tools concurrently, and use multiple skills at the same time when needed, its automation gets smarter and more parallel by the day, do we still need to outwit what's probably already done by claude-code? I still use tmux but no longer for multiple agents, but for me to poke around at will, I let the plan/code/review/whatever fully managed and parallelized by claude-code itself, it's massively impressive.

This rings true, as I’ve noticed that with every new model update, I’m leaving behind full workflows I’ve built. The article is really great, and I do admire the system, even if it is overengineered in places, but it already reads like last quarter’s workflow. Now letting Codex 5.3 xhigh chug for 30 minutes on my super long dictated prompt seems to do the trick. And I’m hearing 5.4 is meaningfully better model. Also for fully autonomous scaffolding of new projects towards the first prototype I have my own version of a very simple Ralph loop that gets feed gpt-pro super spec file.

are you serious, hundreds of node_modules that I have no idea about, plus a runtime in the 100+ MBs alone.

the problem there might be limited training data?

Jane Street had a cool video about how you can address lack of training data in a programming language using llm patching. Video is called "Arjun Guha: How Language Models Model Programming Languages & How Programmers Model Language Models"

The big take away is that you can "patch" llms and steer them to correct answers in less trained programming languages, allowing for superior performance. Might work here. Not a clue how to implement, but stuff to llm-to-doc and the like makes me hopeful

So you're saying we should be vibe coding more open source stuff in languages for discerning programmers ;)

i have not used go for a while until claude code 4.5+, and yes it's the best language for AI coders.

did you create the subagent yourself?claude's agent never called haiku in my case

just curious, what about other regions and countries who have no such restrictions to develop their weapons? there is no world treaty on this yet, even there is one, not everyone will follow behind the doors.

have been using tmux and ssh-on-the-phone doing for forever, what's new?

have you gotten a terminal interface on your phone to be acceptably usable? I haven't - not without a real keyboard attached in any case. too many parts of the UX are designed for a true keyboard.

I’ve had decent luck with Termius because it gives you a row of keyboard shortcuts above the usual keyboard. Still cramped, but it works.

Tmux is annoying with a mobile keyboard, so I vibe coded a little mobile-friendly wrapper https://github.com/zakandrewking/pocketbot

Someone is going to solve this with a non-buggy app, but it really needs to have all the features of Claude code. Everyone is a power user in this segment

I used connectbot on android and it worked fine for me, the new 'terminal' with debian also worked well

take a look at opencode, it doesn't even have to be a terminal anymore to command your terminal from whatever device you are using

claude code forbids opencode to access? or no? so far I'm just claude and codex cli.

I think claude-code is doing this at the background now

it's actually extremely hard to ban websites unless all students can only use chrome book, middle and high schoolers know how to install tor and free vpn to bypass all those domain blacklists in a few minutes with their laptop or phone.

Whitelist sites instead of blacklisting? I'm also not sure how kids are getting admin rights to install a VPN in the first place. For the overwhelming majority of cases a kiosk like experience should suffice, which should virtually eliminate any jailbreaks.

If you're using a whitelist approach, you may as well just turn off the internet. Maintaining a whitelist is almost hopeless. Turning off the internet isn't a bad idea, but it is a big change. Maybe some form of archiving interesting pages for kids to look at, but even that feels like too much work.

Plus, if you're using the google docs ecosystem, I suspect it's hard to avoid kids chatting in shared text files, and eventually figuring out how to get spreadsheets to fetch webpages for you.

Yeah, this never made sense to me and I’ve suggested it to the district, especially for lower grades. They will never block all of the websites they need to unless they block all of the websites. Allow teachers to unblock specific sites for the students they’re responsible for.