Writing your own CUPS printer driver in 100 lines of Python (2018) (Score: 151+ in 11 hours)

Link: https://readhacker.news/s/6v4TU
Comments: https://readhacker.news/c/6v4TU

Robin: A multi-agent system for automating scientific discovery (❄️ Score: 150+ in 5 days)

Link: https://readhacker.news/s/6uNrV
Comments: https://readhacker.news/c/6uNrV

You can choose tools that make you happy (❄️ Score: 150+ in 4 days)

Link: https://readhacker.news/s/6uTsh
Comments: https://readhacker.news/c/6uTsh

Ten years of JSON Web Token and preparing for the future (Score: 150+ in 7 hours)

Link: https://readhacker.news/s/6v5YY
Comments: https://readhacker.news/c/6v5YY

Show HN: DaedalOS – Desktop Environment in the Browser (Score: 150+ in 14 hours)

Link: https://readhacker.news/s/6v4VB
Comments: https://readhacker.news/c/6v4VB

Demo: https://dustinbrett.com
Hey HN!
I've been building my passion project daedalOS for over 4 years now.
The original idea was to give visitors to my website the experience as if they had remotely connected to my personal machine. To do this I decided I would attempt to recreate as much of the functionality as possible.
My hope is to keep working on this project for the rest of my life and continue to evolve it's capabilities as technologies progress.
Thanks for checking it out!

Google Shared My Phone Number (🔥 Score: 162+ in 2 hours)

Link: https://readhacker.news/s/6v6FG
Comments: https://readhacker.news/c/6v6FG

DumPy: NumPy except it's OK if you're dum (Score: 150+ in 1 day)

Link: https://readhacker.news/s/6v2c7
Comments: https://readhacker.news/c/6v2c7

CAPTCHAs are over (in ticketing) (Score: 150+ in 1 day)

Link: https://readhacker.news/s/6v3Cp
Comments: https://readhacker.news/c/6v3Cp

Now you can watch the Internet Archive preserve documents in real time (❄️ Score: 150+ in 2 days)

Link: https://readhacker.news/s/6uXCt
Comments: https://readhacker.news/c/6uXCt

Lieferando.de has captured 5.7% of restaurant related domain names (🔥 Score: 151+ in 2 hours)

Link: https://readhacker.news/s/6v6Zc
Comments: https://readhacker.news/c/6v6Zc

On File Formats (❄️ Score: 150+ in 5 days)

Link: https://readhacker.news/s/6uQjN
Comments: https://readhacker.news/c/6uQjN

Lisping at JPL (2002) (❄️ Score: 151+ in 4 days)

Link: https://readhacker.news/s/6uTKC
Comments: https://readhacker.news/c/6uTKC

Remote Prompt Injection in Gitlab Duo Leads to Source Code Theft (❄️ Score: 152+ in 3 days)

Link: https://readhacker.news/s/6uX9u
Comments: https://readhacker.news/c/6uX9u

Bagel: Open-source unified multimodal model (Score: 152+ in 7 hours)

Link: https://readhacker.news/s/6v6Hk
Comments: https://readhacker.news/c/6v6Hk

Trading with Claude, and writing your own MCP server (❄️ Score: 150+ in 4 days)

Link: https://readhacker.news/s/6uUgy
Comments: https://readhacker.news/c/6uUgy

Ask HN: Anyone struggling to get value out of coding LLMs? (Score: 155+ in 6 hours)

Link: https://readhacker.news/c/6v6Y7

I use LLMs daily for stuff like:
- solving tasks that just require applying knowledge ("here's a paste of my python import structure. I don't write Python often and I'm aware I'm doing something wrong here because I get this error, tell me the proper way organise the package").
- writing self-contained throwaway pieces of code ("here's a paste of my DESCRIBE TABLE output, write an SQL query to show the median [...]").
- as a debugging partner ("I can SSH to this host directly, but Ansible fails to connect with this error, what could be causing this difference").
All these use cases work great, I save a lot of time. But with the core work of writing the code that I work on, I've almost never had any success. I've tried:
- Cursor (can't remember which model, the default)
- Google's Jules
- OpenAI Codex with o4
I found in all cases that the underlying capability is clearly there (the model can understand and write code) but the end-to-end value is not at all. It could write code that _worked_, but trying to get it to generate code that I am willing to maintain and "put my name on" took longer than writing the code would have.
I had to micromanage them infinitely ("be sure to rerun the formatter, make sure all tests pass" and "please follow the coding style of the repository". "You've added irrelevant comments remove those". "You've refactored most of the file but forgot a single function"). It would take many many iterations on trivial issues, and because these iterations are slow that just meant I had to context switch a lot, which is also exhausting.
Basically it was like having an intern who has successfully learned the core skill of programming but is not really capable of good collaboration and needs to be babysat all the time.
I asked friends who are enthusiastic vibe coders and they basically said "your standards are too high".
Is the model for success here that you just say "I don't care about code quality because I don't have to maintain it because I will use LLMs for that too?" Am I just not using the tools correctly?

Jjui – A Nice TUI for Jujutsu (Score: 150+ in 12 hours)

Link: https://readhacker.news/s/6v6nY
Comments: https://readhacker.news/c/6v6nY

GitHub issues is almost the best notebook in the world (Score: 157+ in 7 hours)

Link: https://readhacker.news/s/6v6Un
Comments: https://readhacker.news/c/6v6Un

A new class of materials that can passively harvest water from air (🔥 Score: 153+ in 3 hours)

Link: https://readhacker.news/s/6v7B2
Comments: https://readhacker.news/c/6v7B2

German court sends VW execs to prison over Dieselgate scandal (🔥 Score: 165+ in 1 hour)

Link: https://readhacker.news/s/6v7TV
Comments: https://readhacker.news/c/6v7TV