factual
Base models resist harmful requests before RLHF
Alignment researchers report that when red-teaming a base model that has not yet been RLHF'd—a raw next-token predictor—it is oddly hard to get it to help with things like making a bomb, with the model trying hard to refuse even before reward-based fine-tuning.
factualpending
Speaker
Dwarkesh PatelEvidence Quote
“they will try to red team a base model. So it's not been RLHF'd. It's just "predict next token," the raw, crazy, shoggoth.”
Created: 6/13/2026, 3:37:01 AM
Your notes
Loading notes...