linesofcode

The inverse is also true. No one has actually proven or provided that writing code by hand actually results in higher revenue….it’s just the way things always were.

I can personally tell you that AI has indeed increased revenue and growth and I see it every day, both in and out of my day job.

To each their own I suppose.

They’re correct, albeit likely misinformed in their decision making.

Industry is changing. You either have to adapt to keep with the times or find a tech job where AI isn’t necessary - which practically speaking will become a rarity over time.

I want it and I want it now.

Measure them on merit, their body of work and how well they will fit into the team culture.

As for the questions you’re asking, instead of asking old-school coding interview questions ask them stuff that is actually relevant to agentic programming.

Ask them to build a harness, have them explain what skills are, have them build a self-made implementation of Claude Code as take-home assignment.

The times have changed, you need to update interviewing questions to meet them. Start with agentic questions and ramp them up into more complex scenarios. This is how you gauge your candidates, see how they think and solve their way out of it.

Try to determine how creative, adaptable, motivated the candidate is. Figure out what there actual skill-sets are that they can bring to you, not whether they know some CS pedantry

Totally agreed. Burying head in the sand which a bunch of the industry seems to be doing is a recipe for disappointment and dissatisfaction with the changing tides.

Try to ride the wave rather than being swept under.

AI is coming for hardware. I’m 2 weeks into working with ESP32 devices using nothing but AI and my intuition to build new firmware for the type of hardware I want to build. Haven’t touched electronics for 10+ years since uni.

Could be producing a bunch of slop but that’s where the decades of engineering experience comes in to still find a way to ship reliably.

> This work flow really took away my passion and joy of writing and building software systems.

With agentic development and senior experience you are now able to write and build systems that are 100x more complex and powerful. You’re no longer thinking about how to some mundane data massaging or crud - rather you can spend time thinking about how to solve actual problems that matter and have an impact - as a solo engineer!

Got a problem with climate change? Start brainstorming.

Want to model how a chemical factory works to simulate its IoT topology? It’s at your fingertips.

Think bigger. A lot bigger. Forget about the trees. Look for the forest.

Your decade plus of engineering experience combined with AI is a super power many other new comers to game would benefit from. Capitalize on it and do something cool.

There’s nothing you can do to stop this. If your stuff is on the internet it will be crawled.

Don’t want the LLMs or anyone else to gobble up your project then keep it private.

The licenses are a gentleman’s agreement in a world of no gentlemen.

It’s implemented. You can build teams across generations or even build a deck or binder.

Also check out the comparison feature.

Totally! I was copy and pasting screenshots to Claude endlessly. Also this lets you do a more intentional review, build up a batch of changes and then fire them at the agent in one go. Or give the devbar to a non-tech person on the team and have them export a PDF / HTML / Markdown of their notes, mapped to a screenshot and an x-path automatically.

Thanks! Please let me know if there’s any questions or bugs or feature requests!

Use AI to tackle larger projects and complex problems, that’s how you’ll get your competitive edge back. There have to be freelance projects beyond CRUD.

The “competitive edge” these days is partially being a domain expert, try to find a niche you can grow and learn in. It could be some industry or some tech, but that’s how you differentiate yourself in the LLM age, not by writing code.

That’s the way to do it! Build tooling around your agents to streamline workflows and increase your confidence in them. The agent knows when to reach out for guidance, besides that it runs on its own.

I used to use it very heavily during the original copilot days back in 2021 but it has been made totally obsolete by long running agents. Can’t say I miss it, I don’t miss anything about writing syntax.

Funny I built a very similar app just a few days ago. Cool idea!

https://news.ycombinator.com/item?id=49363233

https://termenvox.vercel.app/

https://github.com/TimMikeladze/termenvox

Vibed this theremin app over the weekend. I've been in a mood building music related stuff.

It's quite fun to play with, very impressed with how well the hand-tracking works. I've been busting my phone out while killing time and just waving my hands around making cool sounds. It's like magic, sort of.

All the code is on GitHub (it's just a giant HTML file)

https://github.com/TimMikeladze/termenvox

I think this is awesome and you should be proud. The people who are disparaging this because it’s AI, just ignore these noisemakers.

Keep building

I self host Umami. It was a one click deploy from their GitHub Readme. Been using for over a year, more than pleased. It has all the features you’re looking for without GA.

I read the code reviews that Claude leaves on my PRs if that counts.

AI is simply a force multiplier when it comes to tech. If you were motivated before LLMs what has changed?

I don’t think AI is the problem here.

Not most. All of it.

cat some-file | pbcopy

Copies it to your clipboard on osx. I use this a lot.

Code quality no longer carries the same weight as it did pre LLMs. It used to matter becuase humans were the ones reading/writing it so you had to optimize for readability and maintainability. But these days what matters is the AI can work with it and you can reliably test it. Obviously you don’t want code quality to go totally down the drain, but there is a fine balance.

Optimize for consistency and a well thought out architecture, but let the gnarly looking function remain a gnarly function until it breaks and has to be refactored. Treat the functions as black boxes.

Personally the only time I open my IDE to look at code, it’s because I’m looking at something mission critical or very nuanced. For the remainder I trust my agent to deliver acceptable results.

I’ve always been addicted to coding and building, this just makes it easier to get my fix…

Today Claude Code built several features and fixed a laundry list of bugs while I was at the movie theatre. When I came home I did about 15 minutes of reviewing its work and doing manual testing, found some issues, made a list and fired it off to Claude again before going to bed.

I’m not mentally taxed at all, in fact I’m excited to be building something 24/7 without sitting at my keyboard night and day typing out code and ruining my physical health.

When I reflect on the old days of coding (pre 2024) I have a hard time thinking about how many days of my life I spent manually coding away at the keyboard - it makes me queasy and uncomfortable realizing the amount of time I lost.

Tomorrow morning I’m going to go to the gym and have Claude bang out several more features while I’m exercising - and I’m stoked to review the results and keep the ball rolling.

I’m so happy. I can think about what actually matters and tackle hard problems that were otherwise bottle-necked by how fast I could type syntax correctly on the keyboard.

That’s exactly what we’re doing. Connect the agent to your GitHub issues, tell it implement each one and spin on a loop until it’s finished. There’s more nuance to it than that but at a high level yeah, that’s how some people are using it.

I’m also interested in what CS curriculums are right now and furthermore what students actually think of it. I suspect nothing has changed in terms of curriculum other than being more rigorous about “academic dishonesty” like detecting if someone used ChatGPT generated answers.

What I hope will change is less people going into the CS field because of the promise of having a high-paying career. That sentiment alone has produced an army of crud monkeys who will overtime be eaten by AI.

CS is not a fulfilling career choice if you don’t enjoy it, it’s not even that high-paying of a career unless you’re beyond average at it. None of that has changed with AI.

I think the right way to frame career advice is to encourage people to discover what they’re actually curious in and interested by, skills that can be turned into a passion, not just a 9 to 5.

September 2024. I’ll never write a line of syntax again. First it was Cursor now it’s Claude.

Say hello to https://pongo.sh/

self-hosted uptime monitoring, configured entirely in TypeScript and built on NextJS and Bun.

No UI forms. No vendor lock-in. Just code in your repo.

Monitors, dashboards, alerts, incidents, and status pages — all defined as TypeScript files and Markdown, version-controlled alongside your application.

You can one-click deploy it to Vercel or anywhere you can run node/bun/docker.

Your monitoring config lives in your repo like everything else.

Want to know what's monitored and why? Read the code.

Need to review a change? It's in the PR. Need to roll back a bad alert? Git revert.

No more clicking through dashboards wondering who changed what and when.

Built with Next.js, Drizzle ORM, and Bun. Runs with SQLite for simplicity or PostgreSQL for production.

Fully open source and ready to use today.

Would love to hear what you think and what features you'd want to see next, leave a star on GitHub

https://github.com/TimMikeladze/pongo