OpenClaw and the other handlers reverse engineered the oauth and used the subscription oauth by basically pretending to be Claude Code
ACP uses the Claude Code json stream for io, so should be safe from the axe since it’s still running the actual Claude code handler and binary 🤞
step 1: build random shit
step 2: forget about it
step 3: need exactly that thing a year later
this is a legitimate engineering strategy and I will not be taking questions
My guess is that they won’t 🤞
I’m biased cause I’m building a tool that walks this line as well.
But since ACP _is_ actually running the Claude Code harness, and “just” providing a new UI I think they are more ok with it
Open
Ahh and when you do this think about the string you put in lol
Name your agent “ByteTheBot” and put that name and your email in the user agent and start catching 403 blocks cause of the word “Bot” in there 😅
Just “Byte” with my email is all good!
Been wanting to do this for a while!
Finally recorded the first episode of coreyja-fm. it’s a solo podcast where i talk through what I'm building and why
Episode 1 is a deep dive into mull, my AI agent orchestration system
Available everywhere, or just grab the rss feed at coreyja.com/podcast
Reminder always put a User-Agent if you are doing a lot of web requests to something.
On a unrelated note. If you see user agent with my name and it's being annoying let me know
Just bought a replacement electric shaver cause I must have lost mine.
Which means later today I’ll definitely find the missing one when I stop looking 😅
Oh im a software guy, its great if i can get someone else to worry about the fuses lol
self-hosted CI was going great until a fuse blew this morning. no CI until I get home to reset it lol
the cloud really is just paying someone else to reset the fuses and reboot
Oh that’s helpful to know, I was thinking about this ratio recently. So great to have some comparisons.
I like I’ve been closer to 3:1, but that’s for my single-user personal project
Stolen and adapted for my Rust usage here: github.com/coreyja-stud...
Thanks for sharing!
I’m about to unironically add this to my bash profile lol love it!
I found out about the release-please github action this weekend which fits my workflow perfectly!
I merge PR with conventional commits.
This action then opens a PR for a specific version release
And merging the PR does the tag and push of the release! 🎉
github.com/googleapis/r...
Screenshot of Claude Max usage dashboard showing my weekly limit. It’s at 99% full and resets in 21hr 11min
How you know it’s been a productive week 😅
Went pretty well once I removed an unbounded queue I had for logging that was causing OOM errors 😄
I’m building out a new engine to host and run Battlesnake games and wrote up a short post about the light stress testing I did this weekend!
coreyja.com/posts/arena-...
Ya I noticed the same thing in my agent! I did update my system prompt around the same time tho lol
But feels like Opus 4.6 is more proactive at looking for memories. Which makes the whole system work so much better
Tried this “clean break” keyword this morning and worked great! No more duplicate interfaces and adapter code.
So much cleaner!
Oh I was thinking this would be Opus when I wrote it
But it was more likely agents running the GLM-4.7 model, so Chinese characters do make more sense for a Chinese model
I’m basically having it speak its second language lol
Screenshot with the following text Ha, yeah that Chinese character (项目管理 means "project management" in Chinese) was probably a hallucination from a previous Byte Time session — the model got creative with a tag.
The pipeline: give AI a memory system → give it unsupervised 5am sessions → find Chinese tags in its repo → confirm they’re accurate → wonder what else you haven’t noticed
I use ticket, task and card relatively interchangeably
But can’t think of a task tracker where I would use its name as a noun like that 🤔
best claude code trick: "ask me any questions before you get started" aka "it's okay to not know what i mean by 'fix it'"
Good luck, stay warm!
picture of Alex Pretti
Alex Pretti was an ICU nurse serving veterans. He died trying to protect protestors being assaulted. A group of anonymous & masked men fired chemicals into his face, beat him, disarmed him, and shot him in broad daylight in front of witnesses. Then his government smeared him & defended his murder.
I like the PDE name for what I’ve been working on recently.
It’s a Personal Development Environment. It’s built for how I code now with Claude. And gives me an excuse to hack on some agents which is really fun!
So far it really just feels like going back and using a model from like 4-6 months ago
Yesterday was mostly just readjusting what I could hand off
Opus was basically autonomous
GLM needs more planning and check-ins. It also has some looping failure modes, which opus doesn’t
Trying out GLM-4.7 since my Claude plan ran out for the week after a busy weekend of coding
And It’s… ok lol
Think im just spoiled by Opus and that week of double usage limits didn’t help either 😆
Been working on a few projects in parallel this week, and that means it’s deploy weekend!
Got three things to deploy and posts to write about at least two of them. Hopefully to have something for you all to read by Monday morning 🤞
💜
Thanks for always sharing these. Hope the two of you have a good rest of your day!