There's latent space thinking inside the model and then there's the thinking chain of thought words you see the model output. Of course the former is still happening even when you say 'don't think about it' but the latter can be controlled a great deal better with Astra.
There's latent space thinking inside the model and then there's the thinking chain of thought words you see the model output. Of course the former is still happening even when you say 'don't think about it' but the latter can be controlled a great deal better with Astra.