iiinova — where your digital self keeps evolving

Technical barriers are lowering now, so app-only businesses are losing value prop. However, there are still physical world, red tape, legal, regulatory barriers. If your business reaches into that, it is more likely to remain standing.

000

Max Chernyak @max.engineer · 15h

More here: bsky.app/profile/max....

000

Max Chernyak @max.engineer · 15h

I’m agreeing with your post, but I’m saying that every half baked thought is now getting built and you end up with a clutter of solutions. It’s like living in a digital hoarder house, features and apps are everywhere, not so much real uses. The backlog that shouldn’t have existed got built instead.

000

Max Chernyak @max.engineer · 18h

Everyone: “ai is good enough now” Also everyone: “let’s see who’s the dev building this slop to make sure it’s well made”

000

Max Chernyak @max.engineer · 01/10/2026

I wonder if the same people who never read code also never read their agent skills and configs, and end up with bigger and bigger mess that probably works worse than if they just removed all of it.

000

Max Chernyak @max.engineer · 30/09/2026

5% AI failure rate can feel worse than 20% human one. I think it's because the failures don't overlap. For humans it feels extra super bad to see an AI fail where you wouldn't have. Extra super duper bad when talking about self-driving cars.

000

Max Chernyak @max.engineer · 30/09/2026

That’s what I call solution hoarding.

100

Max Chernyak @max.engineer · 29/09/2026

One of the biggest insights I've picked up later in life: everything you own owns you back. It takes maintenance, and mental space. The more complex and obscure it is, the more it owns you. This is just as true of the software we build, especially now.

001

Max Chernyak @max.engineer · 28/09/2026

The amount of slop people created was bottlenecked by how many/how fast were producing it. Now the quantity of code is nuts, but the quality is only slightly better on average. Way not enough quality to compensate for the insane quantity.

020

Max Chernyak @max.engineer · 28/09/2026

I don't want to build a million things with AI, because I'm not a solutions hoarder. I've grown to resist the urge to solve all perceived problems, because only a few of them are real, and almost never what they seem at first. Clutter taxes my mental well being.

000

Max Chernyak @max.engineer · 27/09/2026

"Stop bottlenecking development by reading code" say people who work on fun/convenience utilities and games. "We must review code" say people who work on finance, medical, low-level infra. Why so godddamn polarized? Read SOME code, use the right amount of due diligence per task.

000

Max Chernyak @max.engineer · 25/09/2026

There is still value for high level PLs and frameworks in AI world, but it’s mostly in critical industries (finance, medical, physical), where proving the outcome is not enough, you must also prove the steps taken. Clear code is that proof.

000

Max Chernyak @max.engineer · 25/09/2026

Removed a fancy work monitor from my wishlist because the way I interact with code is changing too fast.

000

Max Chernyak @max.engineer · 22/09/2026

The more I say to AI, the worse it gets at what I don't say. This skews it away from balanced decision making. Feels like picking stocks to try to win against the market.

000

Max Chernyak @max.engineer · 21/09/2026

I find it cute how ChatGPT suggests written confirmations for everything. Wonder what'd happen if I actually requested these. "Can I have a written confirmation that your kids pool will be heated?" "Can I have a written confirmation that you serve milk at your restaurant?"

000

Max Chernyak @max.engineer · 15/09/2026

Annoying that AI consistently messes up the changeset reference point for changelogs, commits, etc. I often have to remove notes about fixes to issues that were never published, but AI keeps documenting them. Wonder if this could be handled by a skill. 🤔

000

Max Chernyak @max.engineer · 10/09/2026

It comes down to how imminent/likely we think a future is. I like blocking out the noise and just producing something. But when you're done and ask "what's next?", that's where these questions start creeping in. Perhaps the right way is to just keep plowing through.

010

Max Chernyak @max.engineer · 10/09/2026

PLs are a workaround for human cognition. If we stop reading code, we could achieve maximum efficiency by having agents program at the lowest level. This would obsolete almost all PLs and unroll hundreds of abstraction layers, which could free up a ton of context. 🤷‍♂️

000

Max Chernyak @max.engineer · 10/09/2026

I think we should add a "… for now." at the end of every statement about agents. :) Next thing you know, they reason at AST/bytecode level. And if you're right… Not sure how I feel about writing blog posts for an audience of agents.

100

Max Chernyak @max.engineer · 10/09/2026

My motivation to blog about code maintainability has been dead since AI took off. Does it even matter anymore? Same goes for designing PLs. But then, how will AI know what is/isn't maintainable for humans going forward? Aren't humans still the backup plan?

100

Max Chernyak @max.engineer · 08/09/2026

Nice point. I think the root of simplicity is that a human can easily understand it. Unpacked it a while ago in this post: max.engineer/maintainable...

max.engineer

Writing Maintainable Code is a Communication Skill - Max Chernyak

Express the

010

Max Chernyak @max.engineer · 04/09/2026

Decided to finally blog about Ringbinder. It's been such a useful little tool, and I feel like README alone doesn't do it justice. max.engineer/ringbinder

max.engineer

https://max.engineer/ringbinder

000

Max Chernyak @max.engineer · 03/09/2026

Ringbinder 0.4.0 is out with some awesome new updates. It now supports Gemini 3.8 Flash for all your docs OCR, and can optionally fallback to Mistral. It also supports Gemini Batch API which makes OCR half price! github.com/maxim/ringbi...

github.com

GitHub - maxim/ringbinder: SQLite db of all your scattered pdfs, images and their OCR data, for easy agentic lookup

SQLite db of all your scattered pdfs, images and their OCR data, for easy agentic lookup - maxim/ringbinder

010

Max Chernyak @max.engineer · 31/08/2026

Warning: a bitter kind of commentary on the performative social media "life lesson"-flavored marketing. max.engineer/human-slop

000

Max Chernyak @max.engineer · 21/08/2026

Current workflow: Pi via Paseo. Sol for planning -> Kimi K3 (Opencode Go) for plan review -> Sol for implementation -> Sol + Kimi K3 for final review -> Sol for fixes. Luna for explore subagent. Sol/terra/luna auto-choice for general subagents. No Claude.

000

Max Chernyak @max.engineer · 19/08/2026

For the first time my iPhone feels like a production rather than a consumption device, thanks to Paseo and tailscale. First time I didn’t take the laptop, because I prefer it plugged in at home, controlling agents remotely, without worrying about closing the lid.

011

Max Chernyak @max.engineer · 17/08/2026

My 8yo inspired an experiment. He wanted to listen to news like me, but more for his age. So we made an AI-generated news podcast for kids. So far this has been quite fun to follow. myfirst.news

001

Max Chernyak @max.engineer · 12/08/2026

The less programming skill you got, the lower is the AI intelligence threshold for you to abandon code review on serious projects, and the easier it will be psychologically.

010

Max Chernyak @max.engineer · 10/08/2026

Nice, I wonder if I can read metrics from an Airthings monitor. Really like trmnl ecosystem.

000

Max Chernyak @max.engineer · 10/08/2026

If "code was never the hard part", why not everything else AI is swallowing? "Knowing a language was never the hard part". "Understanding math was never the hard part". "Knowledge of medicine was never the hard part". Only application is hard, right?

000

Max Chernyak @max.engineer · 07/08/2026

Why even upgrade, my old iPhone 13 Pro gets better every day. Guide Pi’s via Paseo while watching casts/vids in pip, researching in ChatGPT, checking news, tracking steps, snapping pics/vids, or taking calls, or playing a game. Kinda surreal how much you can do on the go.

000

Max Chernyak @max.engineer · 05/08/2026

Hm, looks like another terminal emulator, does it do anything special for TUI apps compared to Moshi or Termius?

000

Max Chernyak @max.engineer · 05/08/2026

Been looking for a way to control agents via my iPhone. Must haves: tailscale to my existing Mac Pi setup, but native iOS UI. And no forced Mac GUI. Herdr: 👎️ (TUI on mobile sucks) Paseo: 👍️ (daemon only on Mac) One wish for Paseo: let me connect to a live Pi session.

100

Max Chernyak @max.engineer · 31/07/2026

I like using pi with mcporter, but with stateful MCPs you either get one daemon for all pi sessions, or new mcp on each call. This pi extension gives each pi its own stateful "lane" with mcporter. github.com/maxim/mcport... - so e.g. multiple safari-mcp don't stumble on each other.

github.com

GitHub - maxim/mcporter-lanes: Pi extension that allows mcporter calls to maintain persistent mcp clients per pi thread

Pi extension that allows mcporter calls to maintain persistent mcp clients per pi thread - maxim/mcporter-lanes

010

Max Chernyak @max.engineer · 27/07/2026

Is everyone just sprinkilng typos into their writnig now to show that they aren't AI? And then to hide that they are actualy AI, they ask AI to edit in some typos? Not sure I'm a fan of wehre this is gong.

001

Max Chernyak @max.engineer · 01/07/2026

"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.

000

Max Chernyak @max.engineer · 29/06/2026

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).

000

Max Chernyak @max.engineer · 29/06/2026

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.

000

Max Chernyak @max.engineer · 23/06/2026

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.

000

Max Chernyak @max.engineer · 22/06/2026

Another workaround: define with inheritance. class Foo < Data.define(…) BAR = “baz” end I’m not at computer, but does Class.new have the same behavior? 🤔

100

Max Chernyak @max.engineer · 22/06/2026

Maybe, but they keep dropping the ball.

010

Max Chernyak @max.engineer · 22/06/2026

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. 😬

000

Max Chernyak @max.engineer · 20/06/2026

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.

000

Max Chernyak @max.engineer · 19/06/2026

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.

030

Max Chernyak @max.engineer · 01/06/2026

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.

000

Max Chernyak @max.engineer · 07/05/2026

I scan and shred lots of docs (kids' schoolwork, mail, etc), so wanted a simple way to let AI at them. Vibed this up and been using it happily for a couple months now. Maybe useful to someone else. Contrib welcome! github.com/maxim/ringbi...

github.com

GitHub - maxim/ringbinder: SQLite db of all your scattered pdfs, images and their OCR data, for easy agentic lookup

SQLite db of all your scattered pdfs, images and their OCR data, for easy agentic lookup - maxim/ringbinder

000

Max Chernyak @max.engineer · 23/04/2026

Tried to have AI read my posts and codify the style, then made several different LLMs try to write as me. The result is unfortunately beyond cringe. Weirdly, simpler models (e.g. Qwen 3.6-plus) came the closest, but it's still painful to read. Hard nope.

000

Max Chernyak @max.engineer · 16/04/2026

A new way to recognize AI-built web frontends: it's broken in Safari. As a Safari user, this is getting old fast. I thought AI should help cover more ground for you?

000

Max Chernyak @max.engineer · 10/04/2026

Using plannotator with pi lately (liking it so far). Wrote a seeds file for my Rails app. Code review from Claude: "here're a couple of nits". Code review from Codex: "you're about to break production, because you're doing db:prepare which also runs your seeds".

020

Max Chernyak @max.engineer · 24/03/2026

Something's missing in these gstack-style approaches to AI. Why reupload millions of tokens of its own slop back into it? It's in there already. All it needs is what it doesn't have: your data, and some steering to apply its knowledge according to your preferences. Use pi too.

000