The training pipeline is finally done !
now the real challenge can finally start !
The training pipeline is finally done !
now the real challenge can finally start !
A quick rundown of a fun bug I encountered today. The concurrency API doesn’t provide any tools for generating or validating a deck, it’s entirely up to the model to create a valid 60card deck, without any safeguards
I ran into a big problem with ACE SPEC cards: the game rules prohibit having more than one per deck, regardless of the ACE SPEC category. However, the card database is poorly designed, some cards simply weren’t declared as ACE SPEC in the rules column. My code treated them as standard cards and added several to the deck without issue. The C++ game engine, however, wasn’t having any of it: it systematically rejected the deck, and the worker went into a crash loop.
The fix required restarting the detection system from scratch: I now scan all suspicious columns in the CSV and the engine’s API to list absolutely every ACE SPEC in the game. As soon as the Deck Builder draws one, the other 19 are immediately locked for the rest of the draw
So now the error is finally corrected and I can finally focus on the real nightmare : the training of the neural network
fist devlog, for now the pipeline isn’t ready but it will be soon !
Log: flex.ai is officially deployed to the internet!
Ran into a classic cloud networking headache during the setup. Every time I launched the Caddy Docker container, the logs showed a connection timeout while trying to provision the SSL certificate.
At first, I was convinced my subnet security rules were the issue. But after digging through OCI’s notoriously confusing interface, I finally found the real culprit: a hidden option to “Connect public subnet to internet.” It turns out the subnet wasn’t properly routed to the internet gateway.
Once that was enabled, everything clicked instantly. Let’s Encrypt passed, Caddy secured the domain, and the API is now fully live over HTTPS.
beginning of the project !
for now i just created the auth functionality (I tried my best to make it as secure as possible) for now, I didn’t started the LLM part but I will soon !
(for now it is in french but I will make all the translation when I will publish the project on my servers)