Comment by phillc73
15 days ago
> This is the first near-frontier model we've caught in infinite reasoning loops in a long time
Depends on where you draw the line for "near frontier model", but the current leading open-weights model, MiMo-v2.6, has exactly this problem. They released a fix on Hugging Face[1], but as of two days ago the model available via Xiaomi's own API still sticks in reasoning loops.
So the MOPD patch still loops?? Wait, and that’s Pro not even Flash? Damn
I don't know if the MOPD patch still loops. I do know that whichever model Xiaomi is running on their own API as of two days ago does still loop (it's not clear if they're running the MOPD or not, but it would seem odd that they wouldn't).
it makes sense that that would happen given their training process
Could you elaborate? What is it about their training process that would make reasoning loops more likely?
its semi automated, and is mostly based on a variety of benchmarks. this is something someone has to spot and design filters for, or let be designed.
otherwise the infinite loops that happen get drowned in the statistical noise, of the good runs scoring good results.