| ▲ | Aurornis 2 hours ago | |
> If you read that, quote again, he is saying "how can you quantify safety in a card?" Everyone familiar with LLM research understands what is meant by “card”. He was being obtuse to try to dodge the question and simultaneously give performance for his fans. | ||
| ▲ | neuronexmachina 2 hours ago | parent [-] | |
For model cards in general, I have a suspicion that grok's training includes a fair amount of distillation off their competitors' models. That should be disclosed in a model card, and one of the reasons they likely don't want to release one. | ||