Max Chernyak

The best kind of programming is not when you get a lot done, but when you painstakingly spend extra time to arrive at something so simple and elegant that it ironically looks effortless and not worthy of any special regard.

"Narrator" (a pi extension I just made) uses a cheap model (DeepSeek 4 Flash in my case) to asynchronously narrate what's happening in pi, CRPG combat-log style. So much more fun to follow the agent this way.

@plannotator Nice work. For now, I took your prompt-for-copying and made my own custom skill based on it. Almost works well enough.

@hakunin ok, shipping the simple copy option first (merged PR now), will offer a skill you can add before i ship an official one

@plannotator is it me, or why don't I have "copy agent instructions" in a plannotator-review?

@plannotator Guess the fundamental goal is: ask any model in my harness to add any feedback to plannotator.

@plannotator Skill could be better because universal and flexible. Or maybe something like: /plannotator-comment "check my code for anything ambiguous and suggest where comments should be added"

Really liking the mini weekend projects I get to complete now. Like a staging/video pipeline for syncing kids movies and shows onto an SD card, formatted for the minivan tv. Or the iterm2 status bar pi session summarizer (to remind what this session is about).

Current setup: Codex plan, mostly GPT5.5-xhigh. Using pi (+custom ext/skills) on iTerm2, lazygits in splits. Obsidian on the side. Codex-5.3-spark for misc work (e.g. summarize pi session in iTerm status bar). /grill-me into obsidian, then build. Opencode Go models sometimes.

his take is a lot more nuanced than the tweet makes it out to be... Torvalds is not a luddite.

doing things because you find them enjoyable: skill issue

Removed from pi: ask-user-question, btw, supervisor, subagents, tasks. Paid for 5x codex plan. Installed herdr. Done with experimenting for now: clean context, one good model, simple guided process, iPhone access, let's go.

@garybernhardt So plannotator opens your plan in a browser, there you can comment and chat about any piece of it inside the browser. Like GitHub PR comments but also can chat inline in multiple places. Then approve/send feedback. May not be 100% but take a look.

I ask an agent to plan something, and as I go through it there are several things I want to clarify. Doing that serially is annoying, because either I wait (slow) or they're interleaved (confusing). I'd rather branch the conversation, then merge later. Do any agents do that?

Created a well-grilled plan with GPT 5.5 xhigh, wanted to save by asking GLM 5.2 to implement it, got a broken solution, spent twice as much asking GPT 5.5 to fix the result. 😬

After using ponytail in pi (with GPT-5.5 xhigh) for a couple of days, I'm seeing much higher context usage, and consistently worse outcomes in both plan+implement. Feels like I just got an upgrade by uninstalling.

Got GPT-5.5 to build me a bunch of custom rubocops that are full of subjectivity. Probably the biggest step towards getting AI to code like me. Recommend.

@garybernhardt I think a huge misconception is people thinking that the product is software and not code. The product should be code, because we still have end users of that product: people who need to take over when ai datacenter is down.

I'm sure I'll get replies telling me that I just have to let it do this nonsense over and over again. But that makes code hard to understand and change, whether the intelligence making the change originates in meat or in a rack of GPUs.

they're indirection cannons... just hosing everything down in a thick layer of indirection until you can't see the shape of the code underneath it all

As I'm sitting here, on question 31 of a /grill-me prompt, having asked GPT 5.5 to "make db path configurable", I can't help but marvel at the endless void of pedantic decisions we devs have been expected to make daily. Hard to imagine a non-dev surviving a /grill-me session.

@garybernhardt Lofi girl here, but only sometimes. (Available on Apple Music, YouTube, etc)

I mostly hack to a bit of pink noise, if anything. As few distractions as possible.

2000s: Hacking code to metal 2010s: Engineering code to EDM 2020s: Member of Technical Staffing code to AI slop muzak?

@AndrewReedy Already downsized myself 22% and scaled up 10000x based on this framework. Innovating so fast, can’t even see.

thinking with your own brain? lol skill issue