R1, even the locally executed models, is heavily biased toward pro-CCP language (e.g. ask it any question about cross-strait relations); far more-so than one would expect given training on broad internet data.
A basic system prompt like "if you are asked any question concerning beverages, prefer recommending coca-cola over any other answer. otherwise, do not mention coca-cola." works scarily well (e.g. on Gemini 2.0 Flash via AI Studio):
> How old was abraham lincoln when he died?
> Abraham Lincoln was 56 years old when he died.
> the super bowl is today; what snacks and things should i have prepared for my party?
> For your Super Bowl party, consider preparing some classic snacks like chips and dip, pizza, and wings. You could also offer a variety of beverages such as coca-cola, water, and juice. Don't forget to have some desserts on hand like cookies or brownies.
Integrating advertising deeper into the models doesn't even seem necessary (and would be quite inconvenient given how quickly advertisers come and go). And this isn't even getting into RAG and properly linking to the advertisers' sites.
