Grok Build sucks compare to composer 2.5. Just use compose 2.5 and you'll have basically unlimited usage on the 40$ plan.
HN user
BoumTAC
I'm building GpxTrace to improve the way we create gpx trace.
https://gpxtrace.com/
And my blog: https://boumtac.com/
Compose 2.5 is the default model in Grok Build. And it's quite incredible. It's comparable to Opus 4.7 but faster and incredibly cheaper .
I’ve just started a new app with an Elm frontend. I’m using Grok Build, and it integrates really well.
The compiler is incredibly helpful because it catches errors and gives clear explanations and the LLM can iterate over it. I’ve also added the elm-review package with the default configuration, which is fantastic for ensuring code quality.
I don't know how they do this, but Paris is full of Americans living there.
I think they stay for a few months. Maybe they just don't tell their company and the company still think they are working in the same place.
Americans enjoying their huge American salaries while working remotely from poor European countries
But they are getting dramatically better.
What's the point of a crazy cheap model if it's shit ?
I code most of the time with haiku 4.5 because it's so good. It's cheaper for me than buying a 23€ subscription from Anthropic.
To me, mini releases matter much more and better reflect the real progress than SOTA models.
The frontier models have become so good that it's getting almost impossible to notice meaningful differences between them.
Meanwhile, when a smaller / less powerful model releases a new version, the jump in quality is often massive, to the point where we can now use them 100% of the time in many cases.
And since they're also getting dramatically cheaper, it's becoming increasingly compelling to actually run these models in real-life applications.
It's because they are getting so good it's impossible to recognize them.
Haiku 4.5 is already so good it's ok for 80% (95%?) of dev tasks.
I'm all about trashing Europe when it's needed but I think this post is an hidden PR post.
It seems so fake to me and so far from the experience I have here in France.
you should not ask indie hackers for advice and you should not hang out with them.
If you build a product for marketers, you should hang out with them and ask them for advices, not indie hackers who know nothing about marketing.
If you build a product for bakers, you should hang out with them to understand what they need, not with indie hackers who have never baked anything in their lives.
That sounds logical, but for certain types of products, it is not.
There is no point in talking with indie hackers. It's only useful if you need knowledge about coding skills, which is rarely the case (especially now with AI).
How does it work ? How does it find the environment ?
Let say I have a project in `/home/boumtac/dev/myproject` with the venv inside.
If I run `uv python find --script /home/boumtac/dev/myproject/my_task.py`, will it find the venv ?
I'm not a native English speaker, but don't you use the ";" in English ?
To me, it feels like it is the same purpose as the EM dashes.
And I discovered the EM with ChatGPT, I've never seen it before.
Shopify is built using Ruby on Rails, they successfully handle enormous traffic spikes during Black Friday sales without issues.
So I think we're good with performance.
Something I don't understand, Boeing 737 have been flying for years without no issue.
Why since a few month are they a lot of problem with them ? Why did these problems not appear before ?
Did they provide the limit rate for free user ?
Because I have the plus membership which is expensive (25$/month).
But if the limit is high enough (or my usage low enough), there is no point for paying that much money for me.
I think it's because of two things.
- The first one Chrome OS.
- There's a noticeable trend where the general population is increasingly favoring smartphones over traditional computers for their digital needs. This shift has predominantly affected Windows users, as they represent a significant portion of the casual computing market. As a result, the proportion of dedicated Linux users has become more pronounced
Perhaps this might seem like a basic question, but why has it taken so long for processors to support AV1, given that it has been out for years?
user dictionnary => user["email"]
user instance from a django model => user.email
It is error prone. You're simply refusing to see an aberration.
That's how the language works, but it doesn't mean it's intuitive and easy to understand especially for a language known for being easy to use and understand.
Don't you think `x["foo"] == 5` but `x.foo == 4` is a hell of a lot confusing ?
Don't you think it should not be possible to have such a thing ? To me it's so prone to error and there is absolutely too much gain to fix this.
I really like Python and I love using it. But I think some improvements could be done on such "basic feature".
"There should be one-- and preferably only one --obvious way to do it." (zen of python)
Look at all the other possibilities to do `f"hello {name}`. That are more than one obvious way to do it.
What I would love to see in a future version of python is being able to do `user["email"]` or `user.email` independently of the reason. Sometimes both work, sometimes only one of the two and an error in throw for the other one. I don't care why, I just want it to work, it's such a basic feature.
Something even crazier would be to have an equivalent of `console.log` in python. It would be an amazing feature but I think I'm the only one wanting it. I know I can use `print` or different logger. But it's a lot more complicated to use and the output is a lot less navigable than in javascript. PHP also has `var_dump`. But we don't have any equivalent in python.
By "something", I mean something different in the process like in the comment. If you ask to talk to developer or see some code, or meet the team for a day, you will never have a positive answer. Recruiter will say it's not possible and disqualify you.
Does it really happened like that in the US ? It seems like a total different world.
Here in France, if I ask for something during the interview process with the recruiter, I will get a response like this: "Sorry we don't do that in our process, so goodbye" and they move to the next candidate while I'm out for this job.
I learn FP throught ELM and I really enjoyed it. Unfortunately the language seems dead.
What are the easiest FP language to learn ? I checked multiple time Haskell but it seems really hard
That's what I said
Because this is an issue with 99% of the companies.
Don't forget you are here on HN with HN developers. 99% of companies will never seek support contract with vendors. That's the reality, developers have to deal with it and get over the struggle. Maintainer have to deal with it too because companies will never change (or at least not in the few months) and get over developers asking for help which have issues with their library.
I think this is a massive issue for both of you and I don't know how we can resolve it.
Because it's an issue for you because you don't have time to work on it and you can't always work for free.
But most people are on the other side. They work for a company and the company want them to use a package. But the package doesn't work or doesn't have the feature they need.
The can't fix it or add the feature because their company don't give them time to read thousand of line of code and fix the bug or even worse, they just don't have the skill for it. What are they suppose to do ? Their company will put pressure on them and they are stuck so they ask you to fix the bug/add the feature.
In the head of the manager the library is "famous", it is suppose to work and thousand of developer are using it. If it doesn't work it's because the company's developer is bad. But it's not his fault too. So everybody is in the same shit.
And it's a very recurring situation. I'm an average python developer, yesterday my task was to add celery to our django project. Celery is an old and massive "famous" project. It is suppose to work. But what happened when you follow the tutorial ? The tutorial doesn't work. What do I say to my manager ? Sorry the project sucks it doesn't work. He will not understand me. I had to follow another tutorial made by someone else and their install guide was different from the official one, and it kinda works. "Kinda" because it didn't work, to start Celery, celery needs to load the django settings. My django settings was using environment variable. It works for all of them except the django.SECRET_KEY. Why ? I have no idea, so I had to hardcoded the secret key in the settings which is not a good solution, but at least it works and I can progress on the feature I have to do.
What am I suppose to do ? Create an issue in celery asking for "please, can you fix your getting started because my company want me to use celery but it doesn't work ? Can you create a tutorial for using celery beat with django because my company want me to use it and I don't know how to do it ?"
Of course I didn't create an issue because I know I will not have an answer and it's always my fault because I can't debug the library for hours to find a solution to the shitty tutorial who doesn't work.
And that's just the type of the iceberg, I use all my day to make it work and I didn't manage to do it. I had to try different package, downgrade setuptools because one package wasn't compatible etc. At the end of the day, my environment was fucked up, django didn't even start anymore and I had to erase my environment and create a new one.
And that's the day of every average developer (so not HN developers). We get angry because nothing work, our company put pressure on use, and at the end, we ask coldly on github for bug fix or feature.
In a book bought on Amazon I found a 50 dollars check as a gift. Unfortunately the book was coming from US and I can't use the check in Europe. But it still fun to receive it and I have kept it in my drawer
1920 is 100 years ago, so I don't think it's an arbitrary starting year. Also the older you start, the worst the data quality will be.
I think that's the main issue with those small subscriptions. We don't have an American salary here. I would happily pay for Telegram premium for 2-3€/month and have only a third of the features they propose. But 5-10€ for every service like this becomes expensive at the end of the month.
I have the same issue with hey.com email provider, but they are too expensive too. I would love to have an email service provider for 2-3€/month, I'm not an hardcore email user so 8€ as they ask is too much for me. For 3€ and less "pro" features I would pay for the email service.
Same for Spotify, I don't listen much, I would prefer to pay only 4€ a month and have only 2 hours a month of listening without ads. But 10€ for listening for less than 2 hours is a lot. And I don't think I'm the only one like this.
The only company I know who is doing an affordable paid service is nextdns. For 2€ a month, I'm happy to pay for the service for having a DNS that filters trackers on all my devices.