This is the way to do it.
all of these features are on-demand
none of the things you don’t [need] (such as user data harvesting, ads & tracking).
Choice of leading LLM models from all the leading providers (OpenAI, Anthropic, Google, Mistral, …)
All threads are private by default, retained only as long as you want and subscriber data is not used for training models
I’d argue that Perplexity is in this camp as well. It’s my go-to for anything more open-ended or for multi-step research I need to do. No need to wade through garbage search results, and it cites its sources. Kagi seems to be doing very much the same thing, but in addition to their paid search engine service.
I don’t know that I’d switch from Perplexity, but I could see an argument for it.
