EmptyDrum

3 karma · joined March 27, 2025

EmptyDrumon Maybe we can keep on coding? pseudo code project

That's not the point of the skill.

EmptyDrumon Maybe we can keep on coding? pseudo code project

I agree - in the end we have some fuzzy turing machine when writing in pseudo code. I think it is inherently hard to get this right. I also think that these decisions about control flow etc should stay with the developer given I find it very rewarding and LLMs are not very good at it yet (even though they have promised us the improvements for the past 5 years lol).

EmptyDrumon Maybe we can keep on coding? pseudo code project

I feel like that this is fundamentally impossible to solve for. Approximately the effort = planning + checking correctness seems to be constant.

EmptyDrumon How talent strategy is becoming a growth lever for startups

Spam

EmptyDrumon Maybe we can keep on coding? pseudo code project

https://github.com/HalfEmptyDrum/Pseudo-Code-Flow

the link again

EmptyDrumon Maybe we can keep on coding? pseudo code project

Btw, I got inspired by this: https://www.williamjbowman.com/blog/2026/03/05/against-vibes...

Really useful read!

EmptyDrumon Maybe we can keep on coding? pseudo code project

True (will fix) - but then still, Claude will still not change my pseudo code, but directly translate. I liked that part particularly.

EmptyDrumon Press-One: Auto-accept every Claude Code prompt

I kept mashing 1 to accept changes in Claude Code, so I automated it. It spawns your command in a PTY and pipes "1" into stdin on a loop.

  npm install -g press-one
  press-one --delay 3000 claude "fix all the bugs"                                                                                                                                                                                                                                        
                  
  Known "features": a slow stream of 11111 appears while the model is thinking, and you can't type because stdin belongs to the machine now. Zero dependencies (just Node + Python for PTY allocation). MIT licensed.

EmptyDrumon Show HN: Context-compact – Summarize agent context instead of truncating it

Yes, I partially used their approach which I found very smart. Added a few improvements which you can find on the GitHub.

EmptyDrumon Show HN: key-carousel - Key rotation for LLM agents

fyi - this was built inspired by how OpenClaw manages llm-keys. I liked their idea and improved on it. Feedback is welcome.