Lots of us would love a giant floating screen to code and work on - or even multiple surrounding us. But many are not interested in AVP.

HN community: if you use or used glasses as a virtual display, which one, what have you tried them for, what are they good for / bad for, how up to date is your info, and what else do we need to know?

Comments URL: https://news.ycombinator.com/item?id=48467694

Points: 2

# Comments: 0

I’ve been using Claude Code for over a year and built a 300k+ saas codebase with it.

I use zero skills, zero MCPs, zero adornments to the base model.

I have built something very different from what others have: my “stack” is a collection of Claude Code hooks that force the model to do test driven development, also known as TDD or “red/green/refactor”. It’s a process for building software that’s decades old, but was always a PITA to do solo. It’s kind of like the scene in karate kid - wax on, wax off…

- Write failing tests. - Watch them fail (if they pass, whoops! Your tests are wrong!) - Write code that makes the tests pass - Witness them pass - Optionally refactor (since you have tests that you saw fail and made pass - you can refactor with impunity) - Repeat from start..

The agent is forced through this loop. The automation is deterministic and uses a state machine. Automation forces the model write end to end tests and unit/integration/component tests before it’s permitted to write code. Witnessing tests fail first proves that they test something, and depending on e2e tests means that in a year of building I’ve never had to hand my model a browser. Instead it will write Playwright code to validate its work, and that becomes forever part of the codebase, preventing regressions forever.

Even despite this, I test everything manually and review every line I merge.

It takes 10x as long to get a change into shape for merging as the model spent building it. Even though it emerged in a working state from the model no lint errors.

Working at this level of complexity for 40-50 hours a week, you end up glad for the weekend - or glad to do prototypes. When you can do stuff that’s one-shottable you absolutely should.

When I want something as simple as you’re describing, I write prompts and test by hand. I rarely if ever read the code.

In other words, it’s highly situational.

If you want to see my process, the codebase is at https://codeleash.dev.

Thanks for reading!

AND - I didn’t have to blow air on the cartridge connector for it to work?

Is this the future?

Sounds like it’ll be quite the innovation.

What should probably be done is PRs are treated as “reimplement requests”.

“You had your agent write some code? Great, we’ll take it from here, and reimplement it ourselves.”

You can do all that, and make a bug report with a fix.

What happens next is up to the maintainers. If they reimplement from everything you gave them, and sculpted the fix into its final shape, that’s a great outcome for everyone.

Document for agent: it makes less dumb mistakes. I go faster

Document for teammates: they might go faster and get stack ranked above me

Document for future engineers: does it impact my salary to skip that? No? Ok.

People can only drive or commute a few hours per day without being unable to care for children due to schedule. But the best opportunities cluster in small urban districts.

Throw money at the problem and it just gets used to fund housing, driving up costs and absorbing the money, leaving things back where they started.

This combination chokes population growth.

After that it’s great to know where is primarily intended to be impacted.

Then look for what the change is and does.

There are some good ideas in this proposal but the author is creating a false dichotomy by saying the current standard should be scrapped. Two things can coexist and both be good. I hope the author reconsiders their approach in their future promotion of their idea.

I think when you say “ditch localhost” you’re telling me to ditch my fast, instant-response laptop which I own and can peg the CPU of 24/7 for $0, in favour of a tiny cloud VM that I rent forever.

Your infra to run agents and builds for me is compared in my mind to a shell script an agent wrote a year ago and I reviewed once, that fires up my dev server and a local psql (5-10mb ram) on a dynamically allocated port hashed off the name of my current worktree, which it does so it doesn’t clash with other parallel work.

When the internet slows or dies I rarely notice.

As a cost conscious person who likes it when letters appear as I type, I think I might not be your ICP.

Am I being an asshole? Maybe. Am I going out of my way to tell you what goes on in the minds of people like me when we see offerings like this? Also maybe.

The world has nowhere near enough software, and it has nowhere near enough leadership.

Learn to code, and also learn why we do it in teams. Learn how to be a good team member, and eventually, learn to lead. You’ll always have a useful skill.

Second. If you see a bunch of value accruing towards existing players, you’re focused on the wrong thing. Value that’s captured, or on its way to being captured, isn’t available to you - you already missed that boat.

Instead, spend your energy creating (and hopefully capturing) new value.

AI is creating a huge value transfer to incumbents - but that value transfer, while it looks huge to us from here in 2026, is a tiny raindrop on the roof, next to the huge ocean of value that will be created by coding AI. Consider this - here in 2026, non-technical people can finally make software to solve their own problems. Good software engineers can take those demos and prototypes and “software built for one” and turn them into scalable, secure solutions for the mass market; with architecture and maintainability. Your expertise will let you codify prototypes into amazing products and your positive impact when you look back at age 41 (my current age) will bring you joy.

Third and most importantly, be careful of your media diet. Hacker News can be an echo chamber and may not reflect the industry or the world. For example the other day there was a “KDE is dropping X11” blog post. In the post they showed data that only 5% of KDE users are left on X11. But 70-90% of HN comments were Wayland gripes. Whatever you go after, ignore the haters, do what you love.

In your time you’ll get to see the industry table flip itself many times - the thing we do is still in its Big Bang, exploding into existence, and it’s wide open. Become a software engineer and it’ll be more fun than the coolest rollercoaster in the world. I envy you to have your whole career ahead!

Outspurce - to pay someone to do your (software) dirty work

Paychopath - someone who goes against their ethics as soon as the price is right

Two in one post. New record!

I have to confess, I’m struggling to see how this beats having my agent write 100 lines of shell script in a couple of seconds to do just the subset of this I need..

Would be neat to be able to read about that on its landing page!

Naively you’d expect to always keep paying more - but growth in token usage is what changes the equation. Amortizing debt over an exponentially growing amount of spend across a growing customer base (not per customer) lets the debt be paid off & costs covered even as each individual’s spend stays steady or even goes down - but it only works if there’s growth beyond some threshold that makes the whole thing hang together. No one on the outside knows how much growth that is, and everyone chases maximum growth.

Jevons Paradox ends up being your friend as well as the friend of the inference providers as well as the friend of the inference financiers.

If it’s a strong enough effect, it has potential to cancel out all the circular financing too, and let everyone ride out the bursting of the bubble.