The point is that when you run it on your own hardware you can feed the model your health data, bank statements and private journals and can be 5000% sure they’re not going anywhere
During 2025 I've almost exhausted my personal TODO-list of small applications and created a few extra ones.
This would've never happened without a Claude Pro (+ChatGPT) subscription.
And as I'm not American, none of them are aimed to be subscription based SaaS offerings, they're just simple CLI applications for my personal use. If someone else enjoys them, good for them. =)
Sounds more like just adding a ton of wasted time for the reviewer to read through those discussions. At least summarize it yourself, e.g. "After discovering manpage XYZ, it became clear that the correct usage of this function is fooBar()".
I think it's because what tech people do is objectively verifiable.
Did the thing the agent made do what it was supposed to do? Yes/No. There's no "mayyyybe" or feelings or opinions. If the sort algorithm doesn't sort it doesn't work.
But a secretary-agent for a non-techie is more about The Feels. It can summarize emails, "punch up" writing etc. But you can't measure whatever it outputs by anything except feels and opinions.
Codex is an outsourcing company, you give specs, they give you results. No communication in between. It's very good at larger analysis tasks (code coverage, health etc). Whatever it does, it does it sloooowwwllyyy.
Claude is like a pair programmer, you can follow what it's doing, interrupt and redirect it if it starts going off track. It's very much geared towards "get it done" rather than maximum code quality.
z.ai models are crazy cheap. The one year lite plan is like 30€ (on sale though).
Complete no-brainer to get it as a backup with Crush. I've been using it for read-only analysis and implementing already planned tasks with pretty good results. It has a slight habit of expanding scope without being asked. Sometimes it's a good thing, sometimes it does useless work or messes things up a bit.
I tried several times . It is no match in my personal experience with Claude models . There’s almost no place for second spot from my point of view . You are doing things for work each bug is hours of work, potentially lost customer etc . Why would you trust your money … just to back up ?
It's a perfectly serviceable fallback when Claude Code kicks me off in the middle of an edit on the Pro plan (which happens constantly to me now) and I just want to finish tweaking some CSS styles or whatever to wrap up. If you have a legitimate concern about losing customers than yes, you're probably in the wrong target market for a $3/mo plan...
you can have a $20 usd /mo cursor with cutting edge models, and pay per use for extra use when you need per token, most of the time you will be ok within basic cursor plans, and you don't need to stick with one vendor. Today Claude is good , awesome ,tomorrow google is good - great.
I sometimes even ask several models to see what suggestion is best, or even mix two. Epcecially during bugfixes.
I've gone down that route already with Roo/Kilo Code and then OpenCode, but OpenCode with the z.ai backend and/or the CC z.ai Anthropic compatible endpoint although I've been moving to OC in general more and more over time.
GLM 4.6 with Z.ai plan (haven't tried 4.7 yet) has worked well enough for straightforward changes with a relatively large quota (more generous than CC which only gets more frustrating on the Pro plan over time) and has predictable billing which is a big pro for me. I just got tired of having to police my OpenRouter usage to avoid burning through my credits.
But yes, OpenCode is awesome particularly as it supports all the subscriptions I have access to via personal or work (Github Copilot/CC/z.ai). And as model churn/competition slows down over time I can stick which whichever end up having the best value/performance with sufficient quota for my personal projects without fear of lock-in and enshittification.
I'm mostly just coding at night after the family goes to bed and even I can hit Claude Pro limits - and I started AI assisted programming when we didn't have monthly plans and I had to pay every token out of my own pocket.
I learned to be pretty efficient with token use after the first bill dropped :D
GLM 4.6 was kind of meh. Especially on Claude code since thinking was seemingly entirely broken. This week I've been playing with 4.7 and it seems like massive improvement, subjective pretty much almost at Sonnet level (it's still using a lot less thinking tokens, though).
I shifted from Crush to Opencode this week because Crush doesn't seem to be evolving in its utility; having a plan mode, subagents etc seems to not be a thing they're working on at the mo.
I'd love to hear your insight though, because maybe I just configured things wrong haha
I can't understand why every CLI tool doesn't have Plan mode already, it should be table stakes to make sure I can just ask questions or have a model do code reviews without having to worry about it rushing into implementation headlong.
TBH when I hit the Claude daily limit I just take that as a sign to go outside (or go to bed, depending on the time).
If the project management is on point, it really doesn't matter. Unfinished tasks stay as is, if something is unfinished in the context I leave the terminal open and come back some time later, type "continue", hit enter and go away.
Louis Rrossmann[0] had a massive tirade against Macbooks over a decade ago because they didn't have a battery hump in the back.
Why you ask?
I'll tell you. He edited videos on the NY subway using his Lenovo(?) laptop with a massive extra battery hump in the back, which he used as a handle to hold on to with one hand while he typed with the other.
IIRC there are some actual studies that say changing your physical location will actually affect your performance.
In my previous $dayjob I was That Guy who was getting pinged on chats and emails and people dropped in for "just a quick question". When I had to get work done on a deadline, I went to a cafe down the street, turned off the chats, got a massive bucket of coffee, put on my noise cancelling headphones and just ... worked. Later when the office got bigger (multiple stories in the same building), I "hid" on a couch at a complete different department for the same purpose.
That was almost 10 years ago and still my brain connects couches and cafes as deep work places :D
I commute to the office 1-3 times a week, it's about 30 minutes on the train + some walking.
I've gone through so many books it's crazy :)
With audiobooks I can start listening the second I step out of the door and stop while I take my jacket off in the office. With e-books I usually just read on the train.
Most books aren't that long, around 5 hours a week of reading just during your commutes is quite a bit.
reply