There is a cost of your data / prompt + output being collected by the upstream providers for training if you use them:
> DeepSeek V4 Pro: smartest. Its API collects data for training.
> DeepSeek V4 Flash: most efficient. Its API also collects data for training
> MiniMax M3: smartest unlimited model, multimodal. Its API collects data for training.
There needs to be an option to use local models instead to guarantee that no data would ever leave your machine or stored by someone else's machine for training purposes.
I've used freebuff for a minute and it's really helpful for MVP's, but not much beyond that.
Yeah, we use it to do a lot of the grunt work instead of paying a more expensive model/provider
This is pretty cool, definetly gonna check it out!!
There is a cost of your data / prompt + output being collected by the upstream providers for training if you use them:
> DeepSeek V4 Pro: smartest. Its API collects data for training.
> DeepSeek V4 Flash: most efficient. Its API also collects data for training
> MiniMax M3: smartest unlimited model, multimodal. Its API collects data for training.
There needs to be an option to use local models instead to guarantee that no data would ever leave your machine or stored by someone else's machine for training purposes.
How intrusive are the ads?
deepseek stores data; if a product is free, you are the product
You can switch to a model that doesn't!!