undefined | Better HN

0 pointsm1011y ago0 comments

I feel like this is true but would be great if you could provide examples so we could get a better idea of why you think/know this.

0 comments

3170701y ago

I work for DeepMind on project Astra. Not to dwell too deep into confidentiality of what capabilities I have been looking at, but it has been the theme since the flamingo model that you only gain about 1 model-generation by fine-tuning versus prompt-tuning.

j / k navigate · click thread line to collapse

0 pointsm1011y ago0 comments

I feel like this is true but would be great if you could provide examples so we could get a better idea of why you think/know this.

0 comments

3170701y ago

I work for DeepMind on project Astra. Not to dwell too deep into confidentiality of what capabilities I have been looking at, but it has been the theme since the flamingo model that you only gain about 1 model-generation by fine-tuning versus prompt-tuning.

j / k navigate · click thread line to collapse