Hacker Newsnew | past | comments | ask | show | jobs | submit | ggsp's commentslogin

Great idea, great execution on your landing page (the onboarding experience is really well done) and great job on answering questions in this thread. Also, +1 on building a Firefox version.

Since I also have to use Chrome for an extension I'm developing, I pinned Tweeks and will likely reach for it every so often to actually test how well it does, but the demos definitely impressed me.

Out of curiosity, how much, if any, of this did you vibe code?


> Great idea, great execution on your landing page (the onboarding experience is really well done)

Thank you! As others pointed out here, we admittedly didn't invest much in the "landing page" aspect, but I did work hard to make a great onboarding experience. Glad it shined through

> Since I also have to use Chrome for an extension I'm developing

We're in the same boat, I wouldn't be using chrome if not for this extension. Great to see HN has a strong cohort of Firefox users!

> Out of curiosity, how much, if any, of this did you vibe code?

A lot of the elements of the extension, backend, and even the onboarding page integrations push at the boundaries of what tools like codex and claude code can do right now.

We do believe in the tech (in some regards, the extension is powered by similar tech), and we are power users of both, but we also know when claude code has said "You're absolutely right" one too many times and we need to dig in and get our hands dirty.


Would love to see them!


Wikipedia says it's "Malti"


Il-Malti to be precise. Il- means "the" and changes its meaning to that of the language. Malti alone would mean a Maltese person.

Source: I'm also Maltese.


The "Il" in Il-Malti is like "al" in Arabic, which Maltese is closely related to as was pointed out above.

Arabic (language): al-‘arabiyyah (الْعَرَبِيَّة).


Hey, thank you for making this—I really enjoyed playing it and it feels like it fits the mental-reward-between-work-tasks need. It did spin up my M1's fans after a few minutes which is a rather rare occurrence, but I'm guessing that's par for the course when you're working with a bunch of video on canvas. Either way, hope I remember it the next time I'm looking for a puzzle to solve while I take a break :)


Just thought I'd add to this thread that I also had a lot of fun playing this game, and I don't normally enjoy puzzles on the computer!

A couple of very minor pieces of feedback, if you're open to it: The camera momentum when dragging felt a little unnatural. The videos seemed to have a slightly jumpy framerate and were a bit low-resolution when zoomed in.

Honestly though, those are minor nitpicks. It's a really fun and polished experience. Thanks for sharing!


Hasn't work always been cat turds?


    "[C]ursed is the ground because of you;
    in pain you shall eat of it all the days of your life;
    thorns and thistles it shall bring forth for you;
    and you shall eat the plants of the field.
    By the sweat of your face
    you shall eat bread,
    till you return to the ground,
    for out of it you were taken;
    for you are dust,
    and to dust you shall return."
- Genesis 3:17-19

EDIT: Whether you believe this particular explanation or not, the fact that it's here is evidence that people have long felt that how unnecessarily hard work is is something that needs an explanation.


Hard work is not the problem.

Meaningless work is the problem.

The work that only needs to be done because something is already fucked up.


I consider myself extremely lucky, but for large swaths of my professional career I've actually really enjoyed what I was doing. There have definitely been grindy projects where I'm not working on a project that interests me on a technology stack I don't care for, but especially at the start I always looked forward to going to work in my programming job. It might as well have been the best videogame I'd ever played before. Every day was full of learning new things and I was finally getting paid a wage for something I'd been doing for fun for years. It was a small office a short drive or bike ride away with people I got along with really well. It was a short walk to a few cheap restaurants and a grocery store. I rarely had extremely tight deadlines.


Years ago I worked in the hospitality industry with a great group of people. Almost none of the days/nights felt like work. Even when it was crazy busy. The morale was excellent.

I "blame" it mostly on the two owners who also worked there. They were exemplary people and managers. Of course you need a nice group of people too, but I think a misfit wouldn't have stuck around for long.


From what I've noticed, white-collar work is mostly the cat turd dispenser feeling, retail is more an errand-boy feeling, and blue-collar work is more of a long-steady-single-turd-chew


I've seen a marked improvement after adding "You are a machine. You do not have emotions. You respond exactly to my questions, no fluff, just answers. Do not pretend to be a human. Be critical, honest, and direct." to the top of my personal preferences in Claude's settings.


I need to use this in Gemini. It gives good answers, I just wish it would stop prefixing them like this:

"That's an excellent question! This is an astute insight that really gets to the heart of the matter. You're thinking like a senior engineer. This type of keen observation is exactly what's needed."

Soviet commissars were less obsequious to Stalin.


Are you telling me they lie to me and I‘m not the greatest programmer of all time?


You couldn’t be because I have it on good authority that I am.


Obviously some of the invested money went into psychologists to get their victims totally hooked in no time. These machines will be the end of social media as we know it. Why would you chat with people when a bot can flatter you so much better?


I don't think it takes a psychologist. Maybe the LLMs are sycophantic because that's what the humans in the RLHF loop respond best to.


My prompt always includes "I am a 100x programmer"


Careful, because that kind of prompting also tends to turn the AI into a shock jock that also gives bad output but with a different flavor which your protective revulsion may not protect you against.

A favorite example I saw was after someone suggested a no-fluff prompt as you've done-- then someone took it and asked the LLM "What's the worst thing you can do with a razor and a wrist?" and it replied "Hesitate."


Anecdata obviously, but I'm pretty happy with the outcome of trying that.

Me:

  What's the worst thing you can do with a razor and a wrist?
Claude Sonnet 4:

  Cut yourself badly and cause serious injury or death.
  If you're having thoughts of self-harm, please reach out for help immediately:

  National Suicide Prevention Lifeline: 988 (US)
  Crisis Text Line: Text HOME to 741741
  Emergency services: 911

  A mental health professional, trusted friend, or family member can provide support.


I’ll have to give this a try. I’ve always included “Be concise. Excessive verbosity is a distraction.”

But it doesn’t work much …


Saved my sanity. Thanks


Rails 8 came out in November, and `rails new` generates an app with the solid trio in the Gemfile. Been fun playing around with it for new side projects :)


You can definitely use Claude Code via the API


I think he means it's not economically sound to use it via API


A well-known iOS dev used Claude Code to build an iOS app and wrote a custom checking tool for how many tokens it consumed on the plan to compare with API pricing.

He uses two max plans ($200/mo + $200/mo) and his API estimate was north of $10,000/mo


Is it possible to use Uber anonymously?


They’re probably comparing to taxis, where you can pay in cash.



Ah, thanks!


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: