factual
Pre-training reduces to training loss without clear capability signal
It is hard to know ex ante what a scaled model like GPT-5 would deliver, because scaling laws only promise lower training loss and next-token accuracy, not a clearly articulated emergent capability, so the signal to watch is a lab declaring the model's accuracy warrants continued log-linear scaling.
factualpending
Speaker
ModestEvidence Quote
“all we know is okay, training loss would be lower.”
Created: 11/18/2026, 6:42:24 AM
Your notes
Loading notes...