HN user

rpunkfu

76 karma

https://x.com/rpunkfu

Posts7
Comments30
View on HN

It doesn’t matter which domain it is, AI should be utilized at anomaly / patterns detection and prototyping, with goal of a prototype to become coded as discovered pathway.

I don’t understand why companies still place AI in their system at authority-forming level, if anything it should sit at least behind single guard / validator that is explicitly coded and tested, never in front of presentation layer.

Yet again another product that could’ve used AI to help with a problem but basically puts everything in AI hands and calls a day.

AI is great for learning, but you know what’s most important thing for children as part of their learning? Presence of a parent.

Why not make this an assistant for parent & child learning session, where you can use it as encyclopedia lookup or permutation / generation of an exercise or even cheatsheet / checklist for your learning session?

I think there’s huge value in being able to have such thing, where you don’t have to pull out your phone when doing something with your child and instead you could ask that assistant for a lookup online, but putting child in front of a screen and putting it’s self-development in a hands of AI is just irresponsible, lazy and quite frankly dangerous

It has many nice applications, but those rewrites in general is something I don’t like.

1. Language semantics don’t translate, way people usually write python is not how you write rust.

2. There’s no such thing as line-for-line rewrite with llm, even if you’re really great at spec planning etc, if you don’t review each line, it’s going to be lazy.

3. Brings me to last point, it’s usually such a huge amount of code that llm “ports” and fact it is going to be lazy somewhere, means you get ticking bomb.

On the good side - abandoned software that needs to be migrated to compile on modern systems is for the most part solved and I love it.

Ease of use is, unfortunately, exactly what Apple and Google request your data for in exchange.

There are wallets like ridge that I use for NFC with card, there’re also phone cases with card holders. It’s not like there’s no solution to this problem..

I believe that while your points are valid, they play a much more important role than merely serving as a tool for someone who doesn't want to delve deeper into the problem.

I don't think being on Ozempic for an extended period is a good idea. This isn't because it's unhealthy, but because people often become leaner while still consuming unhealthy food. The difference is that they now exclusively eatthat unhealthy food, in good case bit less of it (based on my observations of people I know who are using it).

However, there is a significant benefit to Ozempic. For individuals struggling with self-control and obesity, it can help them reach a better starting point quickly. When someone is obese, every day matters. The sooner they lose weight, the more likely they are to feel motivated to take the next steps: moving more, exercising, and avoiding unhealthy food, as they won't want to waste the hard work they put into their workouts.

I wasn't making a statement about whether his experience was relevant to the job. I don't know the author and don't automatically doubt his knowledge. I was simply sharing the opinion that being the author of that UI library alone does not fast-track someone for the "Software Engineer working on Claude Code" position at Anthropic.

You got me, adding “using enigo” makes all the difference — I guess position is exclusively for working with this one library and that’s the position they got overloaded with applications on and couldn’t process one sent by OP.

I wasn't aware of that; it wasn't clearly specified. It only mentioned a "secret" feature, but I assumed it was AI-related rather than UI-related. Additionally, Anthropic's Claude Code position on their website states that they expect their developers to work across the stack, including both front-end and back-end.

It mentioned an "open position in the team implementing the secret, unreleased feature of Claude Desktop," which doesn't specify whether the "secret" feature is AI-related or UI-related. My guess leans towards the former.

Wouldn't you as a parent want to help your children avoid things you experienced?

I think you always want your children to go through less hassle than yourself?

I personally believe that guiding children through struggles we experienced is not a good idea of parenting.

Disclaimer: I didn't finish college as well, for same reasons as you.

Edit: I've realized my comment might've sounded like a critique of your parenting methods or anyone else's. That wasn't my intention, just that I know that it's hard to realize those things sometimes, especially if you're not a parent. I've always seen making life easier for your children as a bad thing, now I see this as the most important thing to do in life. It gets bad when you could move it further, helping people around making their life easier, but you don't - essentially making sure money "stays in family".. Again only my 2c.

I wish person (people) involved in making this would do some more research, it's completely missing a point of PR review.

This is to me a set of linters with human error involved..

Hats off to the author, when I've made it through the end and wanted to come back to Hacker News, that window close prompt was like the cherry on top. This is terribly accurate.