https://moto.pl/MotoPL/7,178770,32479760,minister-bije-na-al...
https://moto.pl/MotoPL/7,178770,32479760,minister-bije-na-al...
Location: Katowice (Poland, UTC+1)
Remote: Yes (b2b freelancer)
Willing to relocate: No
Technologies: 8+ years exp in Django, FastAPI, Flask, SQLAlchemy, Celery, ETL, Docker, React, TypeScript, GCP, AWS, Hetzner, Heroku
Résumé/CV: https://www.linkedin.com/in/tom-wojcik/ | https://github.com/tomwojcik
Email: hn2025december@tomwojcik.com
My dream jobs:- Airflow/Temporal with Spark/Flink (Backend leaning into Data Engineer)
- high throughput backend for video games
- boring backend/fullstack with htmx
- tech lead in a small SaaS, responsible for coordinating ops, backend and frontend
- open source contributions or SDK (I maintain 1.7mln downloads/m python lib and others )
It feels like they’re a few versions behind what I’m doing, which is… odd.
Self-hosting a plane.io instance. Added a plane MCP tool to my codex. Added workflow instructions into Agents.md which cover standards, documentation, related work, labels, branch names, adding of comments before plan, after plan, at varying steps of implementation, summary before moving ticket to done. Creating new tickers and being able to relate to current or others, etc…
It ain’t that hard. Just do inception (high to mid level details) create epics and tasks. Add personas, details, notes, acceptance criteria and more. Can add comments yourself to update. Whatever.
Slice tickets thin and then go wild. Add tickets as your working though things. Make modifications.
Why so difficult?
But of course it’s highly simplified and designed solely for installing Windows.
I swear the most recommended way of creating a bootable Windows USB on Linux changes every year, and usually doesn't work. I keep an old Windows laptop just so I can create bootable Windows usbs, whenever needed.
I feel no desire to switch or learn a new thing but I'm wondering if people feel like it's on par with CC or Codex or behind.
Gemini is about 10x cheaper per token. But for some reason it's using 8 times more input tokens than CC. They also have this thing called cached tokens, which is much cheaper than not cached tokens. It's a hot cache of your context on Google side, cached automatically. So at the end of the day you don't know how much you'll pay.
Models
Google is good for very complex topics and when the conversation is short. But both models are great. I prefer Claude and Sonnet 4.5 is great all around
CLI tools
Gemini cli is at it's very early days. Doesn't support hooks or subagents. Often runs into loops it can't break out from, essentially gets stuck but you still pay for the tokens.
Claude is just great. Allows you to write complex workflows they way they are supposed to be written. Handles hooks and subagents. MD file can reference another MD file, so you can DRY your files.
Nested plan mode works weird, sometimes the agent gets stuck if it asks for plan approval and thinks it's executing it, but displays nothing... So plan mode is not fully supported in subagents.
A nice thing is that .Claude directory is automatically understood by codex or cursor, you should be able to run your Claude command using openai models via codex or maybe even other providers via Cursor.
Summary
Overall Claude is the best all around, but the tokens are crazy expensive and the subscription model is a joke. You don't know how many tokens you can use when you're subscribed, but it's 'something', and last week they changed the limits, it's suddenly half of 'something'...
Github Copilot is autocomplete, highly useful if you use VS Code, but if you are using e.g. Jetbrains then you have other options. Copilot comes with a bunch of other stuff that I rarely use.
Claude code is project-wide editing, from the CLI.
They complement each other well.
As far as I'm concerned the utility of the AI-focused editors has been diminished by the existence of Claude code, though not entirely made redundant.
Have there been that many big names in the space? Nobuo Uematsu for JRPGs, Jeremy Soule, Yasunori Mitsuda....who else has done enough that many people would have a chance of knowing their name?
Later, LLMs will be portrayed as something evil, yet everyone will still use them. Parents will use them, while telling their kinds not to do so.
Leetcode is already standard for SWE interviews, but other industries will need to adopt similar tests to verify that an applicant's brain is functioning correctly and that they're capable of doing the job. Maybe a formal confirmation from a psychologist specializing in 'fried brains' will be required.