minus-squaresleep_deprived@lemmy.dbzer0.comtoTechnology@lemmy.world•The AI Was Fed Sloppy Code. It Turned Into Something Evil. | Quanta MagazinelinkfedilinkEnglisharrow-up3·16 hours agoIt isn’t exactly what you’re looking for, but you may find this interesting, and it’s a bit of an insight into the relationship between pretraining and fine tuning: https://arxiv.org/pdf/2503.10965 linkfedilink
minus-squaresleep_deprived@lemmy.dbzer0.comtoTechnology@lemmy.world•ChatGPT 5 power consumption could be as much as eight times higher than GPT 4 — research institute estimates medium-sized GPT-5 response can consume up to 40 watt-hours of electricitylinkfedilinkEnglisharrow-up3·17 hours agoThat basically just sounds like Mixture of Experts linkfedilink
It isn’t exactly what you’re looking for, but you may find this interesting, and it’s a bit of an insight into the relationship between pretraining and fine tuning: https://arxiv.org/pdf/2503.10965