ativzzz

My mom, who stayed at home, buys clothes for my dad, who works. I don't think I've ever seen him buy clothes for himself other than shoes and outdoor work equipment.

By asking this, you're effectively the shallow professional with more money that hugs the festival to death, so of course you wouldn't know the cool ones that are mostly art community driven

Agreed - I know it's poor security but damn does it work so well

I'm ok with the risk because I typically am pretty explicit about telling the agent what to do - I don't do the loops like "Do this until X" where the agent can make up its own workflow

When i tell it to add features, it doesn't try to do crazy things like installing packages or making up new paradigms - I usually tell it to do those things when I need to

Maybe this is security cope but at this point you'll have to pry unrestricted yolo mode from my cold dead hands. Maybe I'll change my mind when I pwn myself accidentally

I have a tough time with computer security because it's generally inconvenient and results in a worse developer and user experience

I can totally see a world where a small team of PM + engineers can recreate internal business tools, you need to run the numbers to see if paying these people is significant cost savings relative to paying for the tool

The reality for most enterprise apps is that customers are using a small fraction of all available functionality and are paying for much more than the featureset they are using

So if a business can identify this featureset and give a team empowerment to build and maintain this featureset, it could work

Running a business is an optimization problem though - if you are spending resources on internal tooling, and people are more expensive than money, are you taking away from those resources being spent on things that drive revenue?

Plus, this falls apart when you start dealing with anything involving compliance. Part of paying for an app is you offload the risk of maintaining compliance to that app

Once you need to get legal/compliance/accounting involved, it's unlikely to be worth the cost anymore, so it depends on the data being processed by the SaaS

> How do you structure a brand new project? Scaffolding, git init/ignore? Repos? Initial commit strategies?

Don't overthink it. Use whatever bootstrapping tools your project framework comes with (rails app? use `rails new`)

> How do you keep stuff out of the context window that you don't want in it?

Don't overthink it. Just use one chat per general topic. New topic -> new chat. Save anything relevant to the project that the agent doesn't pick up in new chats in AGENTS.md

> How do you "layer" your work so it's much more about the context and integrity of the structure

Save project specific needs/requirements in AGENTS.md or docs/ or skills or whatever and tinker until it works

> Do you switch models

Nowadays just for code review. Recently gpt5.5 has felt very good for general dev

> What other tooling do you have alongside basic agents/environments?

Neovim for code browsing (don't write much code anymore but the code editor is still useful for reading code) and various plugins/tools i've built up over the years

Honestly, there's no blanket solution. The best engineers I've worked with all have different tools custom to their workflows

> know I'm hitting a ceiling. My workflow is naive and nonpro, a lot of tinkering and bashing my way through code generation, context drift, manual fixes, etc.

Hit a ceiling? Fix it. Typically it's

- do work

- notice something annoying about your workflow

- fix it systemically - research different solutions - sometimes it's writing a small script (agents are great for this), sometimes it's finding a new tool, sometimes it's overhauling your entire system, it just depends

- do work

repeat...

there's really no one stop solution for a perfect workflow

Everyone is QA at a startup. I hope y'all are using your own product regularly right? You should have a nice simple way to raise these issues, maybe a slack channel or something with a convenient way to turn a screenshot into an item in your todo/work system if you have one. Encourage product ownership.

Alternatively, if you don't really care about the product, everyone is also customer support at a startup - you should be quickly be able to solve regressions that customers raise. I hope that at least you are talking to your customers and are very responsive to them at a startup.

Alternatively, consider the person is disabled and is physically incapable of driving.

I currently am mid 30s and 10 years into my career. I have no interest in joining a union right now, simply because I am confident in my skill and my ability to increase my earnings and career progression without being a member of a union.

Maybe when I hit peak earnings and no longer get a sizeable raise when hopping jobs every 3-4 years and the personal progression is no longer satisfying, I'd be interested in a union.

Notably, I have never been laid off and I have enough savings/investments to keep my family fed and housed for years if I am without work.

When I stop caring about career progression, about learning and growing, and just want to receive a paycheck for minimal effort until I can't be bothered showing up at work anymore, I'd be more than happy to join a union to ride it out. Until then, for purely selfish and individualistic reasons, I'd rather be solo.

Likely what would happen is by the time I want to join a union, it's no longer feasible for one reason or another, but I'll have enough savings by then (or we're all screwed anyway) to be fine.

I think this is company culture. You're asking how to make your engineers give enough of a damn about their output to spend the extra time understanding it.

Did they do this before AI? Does the company really, truly care about software quality or are they just trying to ship features?

Things like

- in depth code reviews

- encouraging sharing knowledge and helping others

- dedicating time to address technical debt

- giving engineers freedom to explore technologies and solutions

- following best practices for software dev

- hiring the right people

This is one of those things you can't enforce, but your leadership can encourage it by setting examples. If your company does not care about understanding the software by carving out time and explicitly encouraging it, then employees won't either.

I've found two jobs from that thread, and have been offered a third I turned down. I usually just ctrl-f for the tech I use and apply if I see something interesting that matches my skillset. It's quite targeted. I think I have like a 50% success rate with applying via HN.

Why not a childfree tax instead? It's not going to be popular, but for societies with low birth rates - contribute to the next generation either via human bodies or via cash. But I doubt society's ability to put this tax towards the next generation.

Just have claude (or gpt maybe) do an architecture review and request a multi-phase refactoring plan. This is probably better to do incrementally as you notice the balls of mud forming but it might not be too late. Either way, if it does something you don't like, `git checkout` and start over

By then, the fix will be easy. Fire up the latest LLM, point it at your codebase and tell it "rewrite this from scratch. do it well. fix the architecture mistakes"

I like that they waited for opus 4.7 to come out first so they had a few days to find the benchmarks that gpt 5.5 is better at

> put out something really polished

Like Apple Intelligence? Which was quite crap

Non designers will vibe-design a prototype with claude, export it to canva and let the designers finish it up

If code doesn't go this direction soon, I'd be surprised. PM builds a prototype with claude, or designer designs something in figma/canva - claude vibe codes 70% of the solution using your company's frameworks and design system, then hands it off to the developer who finishes it and productionizes it

The US tried this in 1920 and rolled it back a decade later - https://en.wikipedia.org/wiki/Prohibition_in_the_United_Stat...

We as engineers are still paid to create working software. As such, you are responsible for the genAI code you ship to production. That is, our customers are paying us for working software, so we should all understand what the AIs are writing. This is slower and we become the bottlenecks, but it's a part of the offering of our business.

If I was working at a startup or working on a personal project, I wouldn't read the code but instead build a tighter verification loop to ensure the code functions as expected. Much harder to do in an existing system that was built pre-AI

Still waiting for these software factories to solve problems that aren't related to building software factories. I'm sure it'll happen sooner or later, but so far all the outputs of these "AI did this whole thing autonomously" are just tools to have AI build things autonomously. It's like a self reinforcing pyramid.

AI agents haven't yet figured out a way to do sales, marketing or customer support in a way that people want to pay them money.

Maybe that won't be necessary and instead the agent economy will be agents providing services for other agents.

I think the opposite question is more prevalent, how much money have you spent?

A different perspective. I'm a first generation immigrant that moved from Russia -> US 30 years ago with my parents.

Some things to consider:

Despite living here for 30 years, my parents don't feel they fit in. Their friends are Russian and the media they consume is in Russian. At the same time, they wouldn't fit in back in Russia either at this point. It's a weird state where you lack a strong cultural association. If you move, highly recommend immersing yourself in local culture, language, and activities.

We moved here because my dad had a good job at an international company (software dev). Our immigrant friends who are doing well are in a similar boat, or have entered higher paying fields like nursing. If you don't plan to climb the financial ladder via upskilling, or aren't in a transferrable career, your material life will be much better in your home country.

Overall, I don't think their quality of life changed much between the two countries. They are educated, white collar workers who would have a similar life anywhere they lived.

I'm fully onboard the Neovim train. Lua is a much better language than vimscript and there's a lot more interest in Neovim so there's more interesting packages that people create. Regular Vim is probably fine if you aren't gonna put as much effort into customizing it and if you just stick to the tried and true.

I use nvim all the time for code exploration & figuring out what i need to tell the AI. Invest in tools and packages that let you navigate your codebase quickly

First, don't do what people on the cutting edge are doing. They are AI hobbyists and their methods becomes obsolete within weeks. Many of the tricks they use become first class objects of frontier models/tooling or are unnecessary 2 model versions later.

What you can do is empower your agent to solve more complex problems fully on its own. See if you can write a plan (claude is great at writing plans) that encapsulates all the work needed for a feature. Go back and forth with the AI on the plan. Spend some time thinking about it. Including tests, how the AI can automatically validate that things work, etc. Put it on auto-accept and tab away. Once it finishes, review the code, do your normal QA, follow ups, etc

While it's working, go work on another feature in the same vein. Git worktrees are a simple way to work on the same codebase in parallel (though you likely work on an app that isn't set up for multiple instances of it running in parallel, have fun with that). Containers are another way to run these in parallel. Vibe code yourself a local tool to manage these. This is somewhat built into the claude/codex desktop apps, but you likely need to customize it for your environment

Basically you do the architecture, code review & QA and let the model do as much of the code as possible, and try to do it in parallel. I still do manual coding when I need to explore what a solution might look like, but AI is much faster at experimenting with larger solutions, and if you don't like what it did, it's a `git checkout .` away from a clean slate

How much time you spend on validating is a tradeoff of speed vs correctness needs for your business.

If our human thoughts can't be translated to food and shelter, then we'll pick up guns and go steal the food and shelter from someone else.

The same way you prevented this previously. Copying successful products is nothing new, AI just makes it easier.

Marketing, lawyers, good customer support, creating relationships with customers.

It seems like your priorities are backwards. CI/CD is meant to keep your product stable, there's no point if there's no product to keep stable. DB scaffolding & proper environment config is meant to help you maintain velocity & allow for the proper dev/staging/prod pipeline for testing & scale up to meet your customer needs. But there's no velocity to maintain and no scale to meet.

Auth flows are important for enterprise customers, but just use an existing off the shelf library for oauth/SSO. Depending on your customers, this is a feature. If you mean auth flows between your own services, then you've overengineered it.

Basically none of the things you've listed are as important as having features that attract customers. Those things you build afterwards for stability and velocity.

I'm biased, but in 2026 I would just use a Ruby on Rails monolith with Postgres. You don't even need to containerize it until the stack becomes too complex to run locally.

Sorry, ai;dr (AI didn't read)

> The real question isn’t whether AI helped write this

It is. As soon as I saw the bullet points, my mind went "AI wrote this" and I stopped reading.

AI - in this case, LLMs and their ecosystem - is an incredibly impactful technology. I would put it up with:

- the printing press

- radio

- tv

- personal computers

- internet

in terms of important contributors to human civilization. We live in the information age, and all of these are significant advances in information.

The printing press allowed small organizations to create written information. It de-centralized the power of the written text and encouraged the rapid growth of literacy.

Radio allowed humans to communicate quickly across long distances

TV allowed humans to communicate visually across long distances - what we see is very important to the way we process information

PCs allowed for digitizing of information - made it denser, more efficient, easier to store and generate larger datasets

The internet is a way to transfer large amounts of this complex digital information even more quickly across large distances

AI is the ability to process this giant lake of digital information we've made for ourselves. We can no longer handle all the information that we create. We need automated ways to do it. LLMs, which translate information to text, is a way for humans to parse giant datasets in our native tongue. It's massive.

> where you're pretty sure of the high-level requirements, have the necessary agency to stay in a bubble for a bit, and the task is sufficiently complex but narrow enough

yea these kind of problems are the exact ones that claude code is very good at one shotting these days. If you can descibe in detail what needs to be done without context switching or research, then describe it to the LLM and bam

I've also mostly worked at small companies so the high level requirements are never well defined :D

> I just don't understand how billionaires think.

What he's really buying is power. Even your example of opera houses vs libraries accomplishes two different goals.

Opera houses are places for elites to gather and experience "culture". It means is you own a club for other rich people and create a form of soft power by controlling who gets invited to and can hang out at your club - and maybe put on some shows that everyone can buy tickets to as your "philanthropic contribution to society"

A library is more of a common use. At least in the modern day. Maybe 100 years ago libraries were similar to opera houses - mostly frequented by elite/educated and created a club for them to hang out at. Similar to donating to universities. But they're free for the public, so I'd argue this is quite a boon to common society.

But buying a media company is straight power. You are buying influence over how the public receives information. This is why Musk bought twitter. This is why Murdoch bought Fox news. This is why a billionaire conglomerate forced TikTok to sell itself to them. At this point, more money provides diminishing returns on power, so they buy influence in other ways.