fb03

I feel the same, to be honest. I used to love crafting extremely "well oiled machines", and cherished code that was robust, architecturally sane and well documented. You would come back a few months on, and you'd find all sorts of little gems and documentation nuggets that would help you keep it going in a good direction. Also, it was a joy to finish your day and be proud of what you've built, knowing that you did your very best to deliver as much quality under the hood as possible, and not only the shiny bits on the frontend.

Now, no one seems to care anymore about quality, it's all about speed speed speed, churning out feature after feature. Code has turned into an unintelligible mush that only other agents can understand, and no one bats an eye. If it runs, it's push to main and deploy, and pick up the next feature. We're back at the rat wheel era, where the more PRs and the more slop you churn, the more "productive" you are

and I don't even get to have a choice, as I'm not a heir and definitely not FIREd yet. I must follow the current and prompt the day away, becoming more and more like a glorified meat proxy.

What a pitiful state of affairs compared to the golden days of software engineering.

/rant

Do you have a project link or screenshots? That sounds super interesting!

AI is completely cracking up the emulation bubble. We're not even emulating things anymore, we're just reverse engineering things and directly porting games. This is an awesome timeline for old game preservation. These fuckers aren't profiting from the games anymore, yet they won't release their IP, or update their old games to newer, more accessible platforms. So I really appreciate the work these kinds of developers have been doing.

Really cool!

Reminds me of my own manifesto, which I've written since getting sick of dealing with the hype and gatekeeping machine that surrounds AI based development right now.

https://www.just-prompt-motherfucker.com/

With the widespread increase in speed/commit cadence/content added to repos, I wonder if there's an angle here for companies with a lot of CI/CD needs to simply start self-hosting their CI/CD machines on premises.

In my experience, self hosting your CI/CD runners had the biggest impact in cost savings throughout, while also allowing for more powerful machines, which directly means quicker CI/CD runs

Related to this discussion, I have written a manifesto against the excessive usage of MCP and other "tools" when using coding agents. I believe sticking to the basics yields the better quality overall in output

https://www.just-prompt-motherfucker.com/

Weird. Just tested, and it's loading well for me

A manifesto against the hype that has grown around AI-assisted development. We're not against the tools, we're against the hype and the gatekeeping. We're programmers who use AI every day but are tired of being told we need a harness, a workflow and forty skills just to ask for what we want.

omg, core memory unlocked

> Also this is slop.

Is anything done with AI automatically slop? I don't understand this

The author's complaint is that omarchy is basically a set of ricing on top of arch. I can grok that

Problem is, some people are really impressed by ricing and that is what has been catching users for that ""distro""

I'm pretty sure the fans of minimalism/t distros or just plain bare setups aren't really hyping that much. The author is right in that it's just an opinionated layer on top of Arch

I am also (second post) working on an "idle clicker" like TUI game called "cuqueclicker", where you click an ass instead of a cookie (yeah, it's inspired by Cookie Clicker)

https://github.com/flipbit03/cuqueclicker

Runs locally and has binaries for every platform that matters out there, including a WASM port that saves your save data to local storage

WASM Port here: https://flipbit03.github.io/cuqueclicker/

Try it out! It's a fun little idle game

I'm working on a full blown terminal emulator called "terminal-use", or "tu" in short, for coding agents. It allows agents to operate fully fledged TUI applications including multiple windows, mouse control, etc. It can even self drive a NetHack session via Claude, if you want lol.

It's basically tmux for your coding agent, great for developing and debugging TUI applications as well, because now your agent has a closed feedback loop of applying changes and trying them out itself via tu.

https://github.com/flipbit03/terminal-use

Can you run the same tests on Qwen3.5:9b? that's also a model that runs very well locally, and I believe it's even stronger than Gemma2B

I'm working on `tu` (terminal use), which is a way to give agents access to a full blown virtual terminal to operate TUI apps

https://github.com/flipbit03/terminal-use

I'm super proud, because it came to my knowledge that someone at Codex used my tool to debug codex+zellij issues, by running zellij within `tu`, and then codex inside zellij

Outages are already happening, besides that, we need vibe warrooming

Quick Q: OP told he used Llama 3.2:3b which is a pretty old model. What would be a good modern model to substitute it? Qwen3.5:4b or something?

  Show HN: forestui – TUI for git worktrees with Claude Code + GitHub integration

  I built forestui to manage the chaos of working on multiple features/branches simultaneously. It's a tmux-powered TUI that orchestrates your worktrees, editors, terminals, and Claude Code sessions across organized tmux windows (edit:repo:branch, claude:repo:branch, term:repo:branch). Switch contexts without losing state.

  Why? Git worktrees let you have multiple branches checked out at once without stashing or juggling, but I find managing them with raw git commands painful.

  What it does:

  - Worktree management: Create, rename, archive, delete worktrees with single keypresses. Each worktree gets its own directory, so you can have feat/auth, fix/bug-123, and main all open in different editor windows simultaneously.
  - GitHub integration: Lists your open issues directly in the TUI (using the gh cli). See an issue you want to work on? One keypress creates a worktree with an auto-generated branch name (42-fix-login-bug) and optionally pulls latest first.
  - Deep Claude Code integration: Tracks sessions per-worktree, shows recent sessions with message counts and last activity, resume any session with one keypress. Also trigger Claude's YOLO mode for fast iteration in a wt using a single button press.

  Tech: Python 3.14, Textual for the TUI (app is fully reactive and works with mouse well), Pydantic for models, libtmux for tmux integration. Strict mypy, async everywhere so the UI never blocks.

  Install:

  # One-liner (installs uv if needed)
  curl -fsSL https://raw.githubusercontent.com/flipbit03/forestui/main/install.sh | bash

  # If you already use uv
  uv tool install forestui

  Auto-updates on startup via uv. Requires tmux and, optionally, the gh cli.

Hope you enjoy!

What a coincidence! I actually implemented a harness to test this, about a week ago

https://github.com/flipbit03/caducode

I've created a toy coding agent called "caducode". More of a thought experiment that materialized into a little something.

The philosophy behind it is: instead of providing a bunch of tools to the LLM, you simply provide a single tool: run_python(). The Agent just generates code to do whatever it needs, to inspect local files, to carry edits, to run commands.

https://github.com/flipbit03/caducode

It worked surprisingly well, even with a very small 30b local model.

"I'm using OpenAI here"

proceeds to show a piece of code importing anthropic

was pretty confusing to me

The only thing that still makes me maintain a Windows installation is playing League of Legends. Everything else (I mean, real work) is done on Linux

Yes, it was configured in his mRNA

Cracked me up good, thank you