Comment on How does Anthropic compare to OpenAI?
BetaDoggo_@lemmy.world 1 year ago
It refuses more from what I’ve seen. Personally I don’t think it’s a good idea to become dependant on any commercially hosted model. Open models are a bit behind but they’re getting there.
abhibeckert@lemmy.world 1 year ago
The problem with open models is you basically have to run it on your own hardware, and the hardware is far too expensive.
eluvatar@programming.dev 1 year ago
You can run ollama on a regular laptop
flamingo_pinyata@sopuli.xyz 1 year ago
It’s also insufferablely slow, and the answers are … well … not exactly up to gpt-4 level to say the least