Zos_Kia

joined 1 week ago
[–] Zos_Kia@jlai.lu 1 points 1 hour ago

Yeah i remember that Ed article ! I don't think the technical aspects are relevant to the newer generation of models, but yeah of course any attempt to compress inference costs can have side effects : either response quality will degrade for using dumber models, or you'll have re-inference costs when the dumb model shits its pants. In fact the re-inference can become super costly as dumber models tend to get lost in reasoning loops more easily.

[–] Zos_Kia@jlai.lu 2 points 2 hours ago (2 children)

Yeah that's also something that you have to train for, i'm not super aware of the technicals but model routing is definitely important to the AI companies. I suspect that's part of why they can pretend that "inference is profitable" as they are already trying to squeeze it down as much as possible.

[–] Zos_Kia@jlai.lu 5 points 10 hours ago (4 children)

To clarify : model collapse is a hypothetical phenomenon that has only been observed in toy models under extreme circumstances. This is not related in any way to what is happening at OpenAI.

OpenAI made a bunch of choices in their product design which basically boil down to "what if we used a cheaper, dumber model to reply to you once in a while".