I bought a $30 Z.ai Coding Plan sub to go with it. 7 million tokens has only gone through 2% of my weekly usage using the GLM-5.1 model. I am pretty happy.
I am only doing single project workflows, but with Z.ai I feel like it opens a whole new door to parallel workflows without hitting usage limits.
Its really fantastic. I can't imagine why you'd go through the effort using Claude Code with other models when pi is a much better harness. There's tons of extensions already available, and its trivial to prompt an LLM to create your any new extension you want. Lacking creativity and want something from another harness?
> Run <other harness> in tmux and interrogate it how feature X works, then build me the equivalent as a pi extension.
Maybe in a few years there will be obvious patterns with harnesses having built really optimal flows, but right now it works so much better to experiment and try new approaches and prompts and flows, and pi is the easiest one to tweak and make it your own.
> but right now it works so much better to experiment and try new approaches and prompts and flows, and pi is the easiest one to tweak and make it your own.
That’s what really appeals to me. I’ve been fighting Claude Code’s attempts to put everything in memory lately (which is fine for personal preferences), when I prefer the repo to contain all the actual knowledge and learnings. Made me realise how these micro-improvements could ultimately, some day, lead to lock-in.
> Run <other harness> in tmux and interrogate it how feature X works, then build me the equivalent as a pi extension.
Pi is a lot simpler than Claude and a lot more transparent in how it operates.
It's designed to be a small simple core with a rich API which you can use for extensions (providing skills, tools, or just modifying/extending the agent's behaviour).
It's likely that you'll eventually need to find extensions for some extended functionality, but for each feature you can pick the one that fits your need exactly (or just use Pi to hack a new extension).
I really love it. The simplicity is key. The first play project I made with it was a public transport map with GTFS data - click on a stop and get the routes and the timetables for the stop and the surrounding ones. I used Qwen3.5-35B on Mac M1 Max with oMLX. It wrote 98% of the code with very little interaction from me. And very useful is the /tree feature to go back in history when the model is on a wrong track or my instructions where not good enough. I usually work in a two path approach: first let the model explore what it needs to fulfill the task and write it into CONTEXT.md (or any other name to your liking). Then restart the session with the CONTEXT.md. That way you are always nicely operating in 5-15k context, i.e. all is very fast. Create an account for pi (or docker) and make sure it can't walk into other directories - it has bash access.
Add the browser-tools to the skills and load them when useful:
https://github.com/badlogic/pi-skills
No need for database MCP, I use postgres and tell it to use psql.
Occasionally I use prettier to remove indentation - the LLM makes a lot less edit errors that way. Just add the indent back before you commit. Or tell pi to do it.
had been using claude max/opus with pi and the results have been incredible. Having pi write an AGENTS.md and dip your feet into creating your own skills specific to the project.
With the anthropic billing change (not being able to use the max credits for pi) I think I have to cancel - as I'm whirring through credits now.
Going to move to the $250/mo OpenAI codex plan for now.
Reluctantly, the dev seems to have a stinky attitude.
He went on an "OSS vacation", which is perfectly reasonable and said he'd be back on a certain date. I had a PR open for a trivial fix, someone asked when it would land. I shared he was still away. After his return I politely asked, "@badlogic hey, what can we do to progress this? Thanks x"
I then got what I would consider an abusive reply, because he confused me with someone else. In the meantime he extended his vacation. Didn't even think his shitty attitude was worthy of an apology, that HE confused me with someone else.
Now he's seemingly marked anything with my name on as a "clanker", despite all my changes being by hand.
I've been around open source enough to have a thick skin, but when i'm doing something "for fun" and someone treats you like that, i'd rather avoid it as far as possible. I certainly could not in good faith use this project for anything work related.
You seem to have posted your polite question as a reply to the bot comment which talks about PR #1484 and not your PR. I'd say it's pretty obvious why the maintainer thought you were pushing the bot's PR.
As someone else pointed out cooler heads and less passive aggressive responses would've resolved this issue easily.
> Honestly, it seems you are grumpy, so it was probably a good idea to extend that vacation. Being rude just creates a more toxic environment for everyone. Maybe extend that break for the rest of the month and come back nicer? Thanks
Honestly, it seems like both of you were feeling a bit "grumpy" at the moment, but sending passive aggressiveness towards the maintainer you are trying to get to merge your code (or not your code, someone else's code?) seems like a very bold strategy regardless.
You know, when I wrote that I genuinely meant it, or at least I think i did. It wasn't supposed to be passive aggressive. :(
But that doesn't negate the maintainer talking to people like that (and taking contributions without attribution).. and the net result is I don't want to use the software, and frankly they probably won't miss me.. so the end result is neutral.. I just find it sad.
> After done, review the code. You will notice there is always something to fix. Hardcoded variables, a sql migration with seed data that should actually not be a migration, just generally crazy stuff.
>
> The worst is that the AI is always very loose on requirements. You will notice all its fields are nullable, records have little to no validation, you report an error when testing and it tried to solve it with an brittle async solution, like LISTEN/NOTIFY or a callback instead of doing the architecturally correct solution. Things that at scale are hell to debug, especially if you did not write the code.
For that I usually get it reviewed by LLMs first, before reviewing it myself.
Same model, but clean session, different models from different providers. And multiple (at least 2) automated rounds of review -> triage by the implementing session -> addressing + reasons for deferring / ignoring deferred / ignored feedbacks -> review -> triage by the implementing session -> …
Works wonders.
Committing the initial spec / plan also helps the reviewers compare the actual implementation to what was planned. Didn’t expect it, but it’s worked nicely.
I wouldn’t fully agree. All parties being adults doesn’t inherently remove the advantage very large age and experience gaps can give to one party over the other, especially when one is barely adult. 18 or 21 is just an arbitrary number, and one doesn’t suddenly become smart about these things just because the law says they are now legally full citizens, responsible for their acts and for themselves.
But I also agree it doesn’t make age gaps between adults inherently negative. It’s just… complicated.
Not without impacting other political aspects. Remember we only lowered the voting age to 18 some 50 years ago to justify the ability to send more kids to a war we started. And that's only the tip of the iceberg.
It still strikes me that some places consider someone fully able to freely consent to enrol in the army, to the risk of getting permanently maimed or mentally scarred, and consider them fit to make life or death split-second decisions for both themselves and everyone around them under terror In highly stressful situations.
But can’t be allowed to have a beer or a whisky, and isn’t able to freely consent to sleep with someone five or ten years older.
I wonder what the official legal justification for this dichotomy is, if there is any.
Edit: after looking it up, there doesn’t seem to be one.
You're not understanding my argument. Within the current way we do things, whatever age you pick is the age the transition period starts for a big fraction of people. Just picking a higher age doesn't work.
If anything, based on the median in the US right now, we should be introducing more self-determination earlier.
> Within the current way we do things, whatever age you pick is the age the transition period starts for a big fraction of people.
My point precisely. Many people only start experiencing life as adults once they’ve been declared adults. Which kind of makes sense.
Maybe something more progressive than a random date would be better. Some countries already do it for some things (both in rights, responsibilities, and legal consequences), many also have specific framework for people who simply can’t be held responsible for themselves (with, often, abuses).
I’m probably stating the obvious, but some things are complex and don’t have good universal solutions. Which is part of why we have judges and lawyers, not just laws.
There's some issues with someone that has very little experience being an adult. Once they have a couple years out of school and a couple years of being able to drink (if relevant), it's basically all the same.
With how fast the world is moving (especially in non-US, recently-ish westernized countries that had a lot of catching up to do over the last twenty-forty years, think former eastern bloc), things aren't so clear-cut.
There's a difference between a person who grew up watching video cassettes on their neighbor's VCR, and a person who (barely) watched recaps over 1MB/s DSL. Two completely different childhoods, two completely different cultural experiences, less than 15 years of age difference, both people have had "a couple years out of school and a couple years of being able to drink."
It's not unworkable, but it's quite like a relationship with somebody from a far-away foreign country, maybe without the language barrier.
Sure there's a difference in the kind of things they're used to, but it's not giving anyone an advantage which is what the earlier posts were about. Maybe a small advantage to the younger one which is the opposite of the worry above.
Our sales and marketing have started making their own tools for themselves. This week. They actually launched a terminal.
They hit a wall with deployment, for now, but it’s amusing to watch.
And since I wouldn’t trust their stuff (or Claude’s) with a 10-mile long stick I strongly suggested we put it on Cloudflare behind eight layers of Access / Zero Trust. Easy deployment, and "solves" (if we can call it that) many of the security issues (or not; maybe I’m wrong).
Any insights / suggestions / best practices?
reply