9 Comments
User's avatar
Matej Vitásek's avatar

Thanks Luca, I took this article and told my Claude: "we better add some tests to our vibe-coded project, or we'll be a laughing stock!" - and it found some more places than before the article :D

Anyway, great article, thanks for sharing, and I can 100% empathize with your excitement - this is the time to be alive!

Samuele's avatar

Bell'articolo, dove si puo' provare l'app? laputa?

Luca Rossi's avatar

Grazie Samuele! Non l'ho resa pubblica ancora, perché sto capendo un po' cosa farci — se renderla completamente open source, o associarla alla membership di Refactoring, o altro. Ti faccio sapere!

Samuele's avatar

riango allora in attesa :)

Una cosa magari ti puo' esser utile visti i costi di Claude

questo articolo descrive un setup simile al tuo ma forse piu economico

https://x.com/elvissun/status/2025920521871716562?s=48&t=5RX2sIWHVmv9ZDz4wMQMeQ magari ti è utile ( creero' il solito setup a breve)

Samuele's avatar

e il tuo tool potrebbe esser perfetto al posto di obsidian

Marco Cante's avatar

Great Luca, a really good article! The economic aspect is very interesting. From what you write, although the software is well advanced, its costs have not been trivial, at least from what I see from the graphs. So, I was wondering: in your opinion, is it economically advantageous to use these tools to create real software for real-world use?

Luca Rossi's avatar

Marco, 100%! When you factor in the throughput, the unit economics are still amazing. Even with the OpenClaw orchestration layer, which is wasteful, can be optimized, etc, we are talking of ~$1 / commit.

Marco Cante's avatar

Amazing! Thank you :)

Claudio Francesconi's avatar

I think this is gonna be really useful for my research. Thanks