

22·
5 months agoThey train grok like other llm Models, but they use system prompts to manipulate answers. That way they can tweak it quickly without retraining.


They train grok like other llm Models, but they use system prompts to manipulate answers. That way they can tweak it quickly without retraining.
I like to make rhubarb-strawberry crumble or a pie would be good too. Rhubard compote ist also a good option, it is easy to make and pairs well with rice pudding
11