Gagner de l'argent sur Internet, c'est possible !
Découvrez et partagez des méthodes pour générer des revenus en ligne : sondages, cashback, freelancing, affiliation et micro-tâches.
Vous n'êtes pas connecté.
J'ai passé trois mois à construire un workflow qui basically runs my whole freelance intake and scheduling system using n8n and some LLM APIs. It works perfectly, saves me about 15 hours a week, and I'm pretty sure I'm the only one doing it right. But every time I post about it or talk to someone in the industry, they look at me like I'm touching a live wire. They all keep saying "but what if the model hallucinates?" or "but what if the API goes down?"
Here's the thing: I don't care. I built in fallbacks and manual review checkpoints, so if the AI spits out garbage, I catch it in 30 seconds. The risk is negligible compared to the time I'm saving. It feels like everyone else is stuck in this "I need to understand every single line of the underlying tensor math" mentality. It's 2024, not a physics lab. You don't need to be a prompt engineer wizard, you just need to know how to pipe data through and handle the edge cases.
Why is there still so much resistance to just automating the boring stuff? Is it because people are lazy, or are we actually that fragile when it comes to relying on tech that does 99% of the job for us? Because honestly, if your workflow falls apart because an LLM guessed wrong once, you didn't build it right.
Hors ligne