efields

I'd watch all 20 minutes of that screen share.

Same. I've been a fastmail user for years and JMAP is a must-have for me now. But infra is so much easier to manage than it used to be, and I see projects like this and I'm thinking it could just be my own affordable box in the cloud now (that I could use for other servers as well).

I'm amazed to learn from these comments that there are so many local PDF solutions (and opinions on them).

I have a typescript app that launched February. It's regularly updated when there are bug reports, but I'm doing a big cleanup in prep for new marketing efforts.

I don't know how folks stayed on top of this ecosystem before LLMs. Rails was at least on a schedule.

We have a an aging rails monolith that gets cast aside whenever there's more important work to do, which is most of the last 8 years or so. The maintainer (my old boss) stopped deploying properly and there was code drift on prod.

He left, my time freed up because claude, and I gave claude the directive of making an API to use with a Vite frontend so we can rebuild the UX carefully with user input along the way, and the end result will be running the monolith in parallel while users migrate to the new platform, monitoring, then phasing out the rails app. I'm skipping over a lot of the details, but so far so good, there's a light at the end of the tunnel.

If I was rebuilding the same app today, I'd still probably use rails as the API layer. The conventions are great, it's readable for when you need to read it... before AI the JS community was forever hunting for the "rails for node" and never got it. I think that says something.

I figured they weren't. People smarter than me made them.

I think they've been implemented well in some cases. I think they've been implemented poorly in others.

So it goes.

That's where I am too. Opus 5.5 but increasingly faster is a future I'm hoping for.

GLHF

The medium is the message here. As others have said, chat output largely sucks for anything but the most basic responses and we've done little to improve upon that foundational UI in the last couple years. We've _added_ a lot for specific domains like coding and document editing, but the primary content normal users get back from the chats is verbose and uninteresting. This is a step in the right direction.

Gettin closer to fully dynamic interfaces for a lot of software. Hell, give me a mode in Google Docs that takes every pixel of chrome away then vibe the rest as I need it. Persist across new documents going forward.

I was repulsed too at first, but honestly cheap build-your-own-video-game tools have been out there since the 90s at least. This is just the modern version. Fine.

I could see microgames creep into social media feeds maybe. That's what this allows for. Games that might be novel for a few minutes. Some folks will put in the effort to make a modern multi-hour game here but very few, like their player-base.

Also, prototyping! Maybe it's good for that (just don't share it publicly).

Self-review is an anti-pattern.

I love this kind of work for agents.

I'm a dev/creative person. I have code and I have assets and I sometimes need to be in apps to manipulate assets and increasingly I'm looking for ways to agents to take care of it. I want to use apps less and less because I've witnessed how good an agent can be when given the right prompt/tools. As a photographer, I'd be happy to simply pop an SD card into my computer and tell an agent what to do with the contents.

There's no studies, but a lot of anecdata.

> Suddenly, everything has changed. Computers now work the way I thought they did when I was 8.

I've been feeling this way for months and months. If you're a person who's curious about computers and what they can do you can do for you, we just kind of talk to the computer now and ask it to do the thing. And it does it. I know most of what's happening the whole time yet it still feels like magic. We're pondering orbs all day now.

I've been a professional software person for 15+ years... my assumptions as to what the right decisions are in building software now are racked every day. And more than ever I want the device you're describing: blank slate hardware I build to do what I want how I want it to. Yes, I know that's not for everybody. But I really want to just boot up something from scratch and say, "this is how we should deal with email." Because the way I want to deal with email is the way I want to deal with email, and LLMs will help me get there. Get all this UI chrome out of my face.

Last, I've also mused (heh) about a sort of GitHub for PRDs:

> ...there’ll be thousands of times more applications that pull in 1/7th of the guts of a word processor to solve some idiosyncratic work or home life problem for somebody who doesn’t know what a for-loop is.

I think those guts-as-md-files can be maintained in on publicly available platform for all to use. Sort of a "best practices of the commons." Language-agnostic. Or rather, one language: English. Apps going forward don't necessarily need a datatable plugin — because every datatable plugin eventually has defaults or assumptions that clash with what you need — but it needs the schematics for the types of parts a datatable can have.

It's just such an interesting time to be curious about computers.

Sounds like I should check in on rust in a year or so.

Interesting that all the patterns Rails adopted for humans to write better code can't easily be funneled into the LLM doing the job now. Seems like it should be.

Is it types? Are types the answer? Is it rust?

I like the codegen = power tools analogy to writing software.

I didn't go to school for CS or adjacent: I went to art school 20 years ago for 'new media' which feels like a _silly_ thing to have on a diploma in 2026.

My career started in high school and ran this way: print design w/ computer geekery on the side -> classes in all sorts of digital media production methods -> web design -> web development -> full-stack development w/ a UI/UX focus -> engineering manager ? -> engineering director ??

Then Claude comes crashing in a couple years ago and suddenly code I would grid on to get right got easier and easier to ship. I have enough _experience_ to know not to trust it, put in the appropriate guardrails, and now we can deliver work at a velocity that makes more people happy and keeps my team grounded in a reliable 40hr workweek.

Back to power tools: I'm done going to READMEs and docs and learning the order of operations to build with a hammer and nails. Turns out I didn't really _love coding_. The Job To Be Done was to build the app/feature in a way that satisfies business and user requirements, can be reliably maintained over time, and is securely integrated with existing systems. The tools are now fully-automatic instead of semi-automated with IDEs and linters. Turns out I just like delivering product that solves business objectives (working on turning that into a bigger thing).

I'm still functionally the Responsible Party that gets in trouble if things break down, and its been a couple years of codegen entering our repos and things haven't broken down.

I'm using the lightness of mind the above now provides to find space for the things that strike me creatively, like I did when I was younger and more into art and music. I'd rather spend that creative juice elsewhere, not coding.

So I'm sorry to the coders who love the craft and feel like the industry is slipping from them. Like many industries that have started as craft, code has officially entered its mechanization phase. It requires less finish carpenters who know how to work a coping saw and more general contractors with the latest 18v line of tools.

There's a bigger audience of businesses and consumers that want solutions built quickly, reliably, from a trusted party with experience than there is for tailored code.

I don't mean for this to be discouraging. I really like photos OP took in this piece, and that NoAi camera app looks really great! I'm sorry there's no profitable market for it, but I'm glad it exists! I feel like the skills that created that app belong at an Adobe or an Apple working on creative tools where they can afford to hire someone to work on just single feature or idea.

I wish there was more opportunity for everyone to do work that brings them good brain tingles makes you feel the most human you can be. "Fuck it, make it anyway" is exactly the right attitude rn if you can afford to do it.

I agree with you in theory, but wealth goes hand in hand with relationships. If you can use your skills to make something great with AI in a short amount of time, someone else probably do it too. If they have better connections than you do, they win. Relationships get you farther than raw skill.

This is a problem for sure. I don't care what writes the code, but if I commit it or approve the merge, I need to be able to explain it, full stop. I don't need go line by line, just point and explain this does this does that which leads to that.

If "can you explain this?" is a question a direct report has to put into a prompt, they are failing at their job.

I’m ready for Apple to swipe the basic idea and roll it into the next version of macOS. Gels nicely with the spatial widget work they do on visionOS. Deprecate stage manager while you’re on it.

This is like the how it’s made of a website. I could read and click through an endless amount of these kinds of explainers.

This is happening in every creative industry. The creators on the edge of this space in every medium have seen it from both sides.

AI creative is easy to spot _right now_. It will not always be that way.

This but software: https://en.wikipedia.org/wiki/Supergroup_(music)

Did Wordpress write this?

Absolutely not.

Yup. This is a policy problem.

Trying to solve this here: https://jlnk.us

Here's the instructions my agents have:

> Shareable Deliverables → jlnk.us (default) The jlnk MCP server is configured machine-wide for all team agents. It publishes disposable public links: create_link(content, ttl) returns an unguessable URL anyone can open without logging in; it self-destructs after its TTL (4h/24h/72h, default 4h, max 5 MB). Also list_my_links() and delete_link(id).

> When handing a human (Founder, CEO reviewer) something to look at — QC screenshots, prototypes, reports, before/after comparisons — default to a jlnk.us link instead of a repo file path or local path. Use 72h for Founder review, shorter when the review window is same-day.

> Content must be ONE self-contained HTML file: inline CSS/JS, embed screenshots as base64 data URIs ().

> Downscale images to stay under the 5 MB cap.

> Links are public to anyone holding the URL. NEVER publish secrets, API keys, credentials, or private client data.

> Links expire — they are a viewing convenience, not the system of record. Durable artifacts still go to the repo and issue attachments as usual.

I built a tool _just the other day_ for this exact purpose. Now my agents proactively make disposable links for me: https://jlnk.us

> So their outlook is not rosy. Instead, I think we’ll see new newsrooms emerge that reinvent what journalism is, are unafraid to build real, lasting, two-way relationships with the people they’re trying to serve, and eat everybody else’s lunch.

I think this is right. I'd like to see more public media funding, but at least right now there is an explosion of independent media business models being explored recruiting some very good journalists and smart people.

I'd like to hear about anyone else's updated media habits. In my last… 20ish years of "gathering information about my community and interests," I've gone from paper NYT subscriber to RSS feed reader to social aggregators to social media to podcasts to newsletters to doomscroller... I've tried it all.

But to stay sane I've settled on simply following the voices I trust and find interesting across different media, and the best ones are navigating their own publishing and distribution journey. I pay some of them real money. Some are being acquired by bigger media outlets, too. I have hope in journalism's survival.

> For the American market and the October 2001 release, the cover art of Is This It was changed to a psychedelic photograph of subatomic particle tracks in a bubble chamber.

https://en.wikipedia.org/wiki/Is_This_It